Upload folder using huggingface_hub (#5)

- Upload folder using huggingface_hub (7bf47f8d245cb9b01e49872c35478b9a319b0fb7)

README.md

@@ -4,6 +4,78 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -77,6 +149,12 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a0094d743e7e13c7a0ebcf10d19f1fe8ff887d02d075e6c5e7b69adb639411
+oid sha256:ab7d7332df354d85019ef8dbda22bf275f3e4612ebbe07ca7d3538dd755384e9
 size 39409357

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9657617f6a4d6bdaeed4dec604e705c37715edc8bcaacfc4f4d9eeeedd18ab
+oid sha256:8e7ecf4519b7c7fe30096c1ce0de750678f8cf403d65a166a096e8155b6d1665
 size 78844421

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9949a4a87ed7ae3838928a0d8e8fa579957588c0727794513b6eaf6d89de58e5
+oid sha256:02822a64d6ab3629baf2f69c5adf000658973be0bc2532154cc2534085175f34
 size 627

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9626955475330926,
+  "epoch": 0.3429796355841372,
   "eval_steps": 500,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -9,611 +9,611 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.01,
-      "learning_rate": 0.00019902912621359224,
-      "loss": 2.6183,
+      "epoch": 0.0,
+      "learning_rate": 0.00019931271477663232,
+      "loss": 2.5587,
       "step": 1
     },
     {
-      "epoch": 0.02,
-      "learning_rate": 0.00019805825242718447,
-      "loss": 2.2731,
+      "epoch": 0.01,
+      "learning_rate": 0.0001986254295532646,
+      "loss": 2.3914,
       "step": 2
     },
     {
-      "epoch": 0.03,
-      "learning_rate": 0.0001970873786407767,
-      "loss": 2.4264,
+      "epoch": 0.01,
+      "learning_rate": 0.00019793814432989693,
+      "loss": 2.4218,
       "step": 3
     },
     {
-      "epoch": 0.04,
-      "learning_rate": 0.00019611650485436895,
-      "loss": 2.3803,
+      "epoch": 0.01,
+      "learning_rate": 0.00019725085910652924,
+      "loss": 2.3414,
       "step": 4
     },
     {
-      "epoch": 0.05,
-      "learning_rate": 0.00019514563106796118,
-      "loss": 2.2789,
+      "epoch": 0.02,
+      "learning_rate": 0.0001965635738831615,
+      "loss": 2.2469,
       "step": 5
     },
     {
-      "epoch": 0.06,
-      "learning_rate": 0.0001941747572815534,
-      "loss": 2.5586,
+      "epoch": 0.02,
+      "learning_rate": 0.00019587628865979381,
+      "loss": 2.3241,
       "step": 6
     },
     {
-      "epoch": 0.07,
-      "learning_rate": 0.00019320388349514564,
-      "loss": 2.3255,
+      "epoch": 0.02,
+      "learning_rate": 0.00019518900343642613,
+      "loss": 2.3266,
       "step": 7
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.00019223300970873787,
-      "loss": 2.2983,
+      "epoch": 0.03,
+      "learning_rate": 0.00019450171821305842,
+      "loss": 2.1856,
       "step": 8
     },
     {
-      "epoch": 0.09,
-      "learning_rate": 0.0001912621359223301,
-      "loss": 2.1903,
+      "epoch": 0.03,
+      "learning_rate": 0.00019381443298969073,
+      "loss": 2.3247,
       "step": 9
     },
     {
-      "epoch": 0.1,
-      "learning_rate": 0.00019029126213592236,
-      "loss": 2.3516,
+      "epoch": 0.03,
+      "learning_rate": 0.00019312714776632305,
+      "loss": 2.3245,
       "step": 10
     },
     {
-      "epoch": 0.11,
-      "learning_rate": 0.00018932038834951458,
-      "loss": 2.215,
+      "epoch": 0.04,
+      "learning_rate": 0.00019243986254295533,
+      "loss": 2.2591,
       "step": 11
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 0.00018834951456310681,
-      "loss": 2.2354,
+      "epoch": 0.04,
+      "learning_rate": 0.00019175257731958765,
+      "loss": 2.1767,
       "step": 12
     },
     {
-      "epoch": 0.13,
-      "learning_rate": 0.00018737864077669904,
-      "loss": 2.2487,
+      "epoch": 0.04,
+      "learning_rate": 0.00019106529209621996,
+      "loss": 2.3478,
       "step": 13
     },
     {
-      "epoch": 0.13,
-      "learning_rate": 0.00018640776699029127,
-      "loss": 2.1957,
+      "epoch": 0.05,
+      "learning_rate": 0.00019037800687285222,
+      "loss": 2.3339,
       "step": 14
     },
     {
-      "epoch": 0.14,
-      "learning_rate": 0.0001854368932038835,
-      "loss": 2.2036,
+      "epoch": 0.05,
+      "learning_rate": 0.00018969072164948454,
+      "loss": 2.234,
       "step": 15
     },
     {
-      "epoch": 0.15,
-      "learning_rate": 0.00018446601941747576,
-      "loss": 2.1787,
+      "epoch": 0.05,
+      "learning_rate": 0.00018900343642611685,
+      "loss": 2.2651,
       "step": 16
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.00018349514563106799,
-      "loss": 2.1839,
+      "epoch": 0.06,
+      "learning_rate": 0.00018831615120274914,
+      "loss": 2.1831,
       "step": 17
     },
     {
-      "epoch": 0.17,
-      "learning_rate": 0.00018252427184466022,
-      "loss": 2.1533,
+      "epoch": 0.06,
+      "learning_rate": 0.00018762886597938145,
+      "loss": 2.216,
       "step": 18
     },
     {
-      "epoch": 0.18,
-      "learning_rate": 0.00018155339805825244,
-      "loss": 2.2554,
+      "epoch": 0.07,
+      "learning_rate": 0.00018694158075601377,
+      "loss": 2.1359,
       "step": 19
     },
     {
-      "epoch": 0.19,
-      "learning_rate": 0.00018058252427184467,
-      "loss": 2.2778,
+      "epoch": 0.07,
+      "learning_rate": 0.00018625429553264605,
+      "loss": 2.1215,
       "step": 20
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.0001796116504854369,
-      "loss": 2.382,
+      "epoch": 0.07,
+      "learning_rate": 0.00018556701030927837,
+      "loss": 2.2179,
       "step": 21
     },
     {
-      "epoch": 0.21,
-      "learning_rate": 0.00017864077669902913,
-      "loss": 2.0803,
+      "epoch": 0.08,
+      "learning_rate": 0.00018487972508591068,
+      "loss": 2.2598,
       "step": 22
     },
     {
-      "epoch": 0.22,
-      "learning_rate": 0.0001776699029126214,
-      "loss": 2.26,
+      "epoch": 0.08,
+      "learning_rate": 0.00018419243986254294,
+      "loss": 2.1813,
       "step": 23
     },
     {
-      "epoch": 0.23,
-      "learning_rate": 0.00017669902912621362,
-      "loss": 2.2557,
+      "epoch": 0.08,
+      "learning_rate": 0.00018350515463917526,
+      "loss": 2.2006,
       "step": 24
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.00017572815533980585,
-      "loss": 2.0614,
+      "epoch": 0.09,
+      "learning_rate": 0.00018281786941580757,
+      "loss": 2.1564,
       "step": 25
     },
     {
-      "epoch": 0.25,
-      "learning_rate": 0.00017475728155339805,
-      "loss": 2.1342,
+      "epoch": 0.09,
+      "learning_rate": 0.00018213058419243986,
+      "loss": 2.2537,
       "step": 26
     },
     {
-      "epoch": 0.26,
-      "learning_rate": 0.00017378640776699028,
-      "loss": 2.1781,
+      "epoch": 0.09,
+      "learning_rate": 0.00018144329896907217,
+      "loss": 2.1975,
       "step": 27
     },
     {
-      "epoch": 0.27,
-      "learning_rate": 0.00017281553398058253,
-      "loss": 2.1828,
+      "epoch": 0.1,
+      "learning_rate": 0.0001807560137457045,
+      "loss": 2.2566,
       "step": 28
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.00017184466019417476,
-      "loss": 2.0557,
+      "epoch": 0.1,
+      "learning_rate": 0.00018006872852233677,
+      "loss": 2.1464,
       "step": 29
     },
     {
-      "epoch": 0.29,
-      "learning_rate": 0.000170873786407767,
-      "loss": 2.1914,
+      "epoch": 0.1,
+      "learning_rate": 0.0001793814432989691,
+      "loss": 2.1421,
       "step": 30
     },
     {
-      "epoch": 0.3,
-      "learning_rate": 0.00016990291262135922,
-      "loss": 2.3306,
+      "epoch": 0.11,
+      "learning_rate": 0.0001786941580756014,
+      "loss": 2.1276,
       "step": 31
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 0.00016893203883495145,
-      "loss": 2.2901,
+      "epoch": 0.11,
+      "learning_rate": 0.00017800687285223366,
+      "loss": 2.0649,
       "step": 32
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 0.00016796116504854368,
-      "loss": 2.1166,
+      "epoch": 0.11,
+      "learning_rate": 0.00017731958762886598,
+      "loss": 2.1835,
       "step": 33
     },
     {
-      "epoch": 0.33,
-      "learning_rate": 0.00016699029126213594,
-      "loss": 2.2927,
+      "epoch": 0.12,
+      "learning_rate": 0.0001766323024054983,
+      "loss": 2.1711,
       "step": 34
     },
     {
-      "epoch": 0.34,
-      "learning_rate": 0.00016601941747572817,
-      "loss": 2.2732,
+      "epoch": 0.12,
+      "learning_rate": 0.00017594501718213058,
+      "loss": 2.2591,
       "step": 35
     },
     {
-      "epoch": 0.35,
-      "learning_rate": 0.0001650485436893204,
-      "loss": 2.1614,
+      "epoch": 0.12,
+      "learning_rate": 0.0001752577319587629,
+      "loss": 2.1471,
       "step": 36
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.00016407766990291262,
-      "loss": 2.1986,
+      "epoch": 0.13,
+      "learning_rate": 0.0001745704467353952,
+      "loss": 2.0861,
       "step": 37
     },
     {
-      "epoch": 0.37,
-      "learning_rate": 0.00016310679611650485,
-      "loss": 2.3506,
+      "epoch": 0.13,
+      "learning_rate": 0.0001738831615120275,
+      "loss": 2.0702,
       "step": 38
     },
     {
-      "epoch": 0.38,
-      "learning_rate": 0.00016213592233009708,
-      "loss": 2.2425,
+      "epoch": 0.13,
+      "learning_rate": 0.0001731958762886598,
+      "loss": 2.1096,
       "step": 39
     },
     {
-      "epoch": 0.39,
-      "learning_rate": 0.0001611650485436893,
-      "loss": 2.2483,
+      "epoch": 0.14,
+      "learning_rate": 0.00017250859106529212,
+      "loss": 2.1062,
       "step": 40
     },
     {
-      "epoch": 0.39,
-      "learning_rate": 0.00016019417475728157,
-      "loss": 2.031,
+      "epoch": 0.14,
+      "learning_rate": 0.00017182130584192438,
+      "loss": 2.2545,
       "step": 41
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.0001592233009708738,
-      "loss": 2.1587,
+      "epoch": 0.14,
+      "learning_rate": 0.0001711340206185567,
+      "loss": 2.1572,
       "step": 42
     },
     {
-      "epoch": 0.41,
-      "learning_rate": 0.00015825242718446603,
-      "loss": 2.1529,
+      "epoch": 0.15,
+      "learning_rate": 0.000170446735395189,
+      "loss": 2.0749,
       "step": 43
     },
     {
-      "epoch": 0.42,
-      "learning_rate": 0.00015728155339805825,
-      "loss": 2.181,
+      "epoch": 0.15,
+      "learning_rate": 0.0001697594501718213,
+      "loss": 2.1922,
       "step": 44
     },
     {
-      "epoch": 0.43,
-      "learning_rate": 0.00015631067961165048,
-      "loss": 2.1168,
+      "epoch": 0.15,
+      "learning_rate": 0.00016907216494845361,
+      "loss": 2.1915,
       "step": 45
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001553398058252427,
-      "loss": 2.2189,
+      "epoch": 0.16,
+      "learning_rate": 0.00016838487972508593,
+      "loss": 2.1594,
       "step": 46
     },
     {
-      "epoch": 0.45,
-      "learning_rate": 0.00015436893203883497,
-      "loss": 2.1362,
+      "epoch": 0.16,
+      "learning_rate": 0.00016769759450171822,
+      "loss": 2.176,
       "step": 47
     },
     {
-      "epoch": 0.46,
-      "learning_rate": 0.0001533980582524272,
-      "loss": 2.0704,
+      "epoch": 0.16,
+      "learning_rate": 0.00016701030927835053,
+      "loss": 2.1223,
       "step": 48
     },
     {
-      "epoch": 0.47,
-      "learning_rate": 0.00015242718446601943,
-      "loss": 2.1273,
+      "epoch": 0.17,
+      "learning_rate": 0.00016632302405498285,
+      "loss": 2.1263,
       "step": 49
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.00015145631067961166,
-      "loss": 2.1639,
+      "epoch": 0.17,
+      "learning_rate": 0.00016563573883161513,
+      "loss": 2.0481,
       "step": 50
     },
     {
-      "epoch": 0.49,
-      "learning_rate": 0.00015048543689320389,
-      "loss": 2.1639,
+      "epoch": 0.17,
+      "learning_rate": 0.00016494845360824742,
+      "loss": 2.1043,
       "step": 51
     },
     {
-      "epoch": 0.5,
-      "learning_rate": 0.00014951456310679611,
-      "loss": 2.0664,
+      "epoch": 0.18,
+      "learning_rate": 0.00016426116838487973,
+      "loss": 2.1678,
       "step": 52
     },
     {
-      "epoch": 0.51,
-      "learning_rate": 0.00014854368932038834,
-      "loss": 2.0539,
+      "epoch": 0.18,
+      "learning_rate": 0.00016357388316151202,
+      "loss": 2.1602,
       "step": 53
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001475728155339806,
-      "loss": 2.206,
+      "epoch": 0.19,
+      "learning_rate": 0.00016288659793814434,
+      "loss": 2.1448,
       "step": 54
     },
     {
-      "epoch": 0.53,
-      "learning_rate": 0.00014660194174757283,
-      "loss": 2.1366,
+      "epoch": 0.19,
+      "learning_rate": 0.00016219931271477665,
+      "loss": 2.1536,
       "step": 55
     },
     {
-      "epoch": 0.54,
-      "learning_rate": 0.00014563106796116506,
-      "loss": 2.1016,
+      "epoch": 0.19,
+      "learning_rate": 0.00016151202749140894,
+      "loss": 2.0339,
       "step": 56
     },
     {
-      "epoch": 0.55,
-      "learning_rate": 0.0001446601941747573,
-      "loss": 2.1042,
+      "epoch": 0.2,
+      "learning_rate": 0.00016082474226804125,
+      "loss": 2.023,
       "step": 57
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.00014368932038834952,
-      "loss": 2.144,
+      "epoch": 0.2,
+      "learning_rate": 0.00016013745704467357,
+      "loss": 2.1407,
       "step": 58
     },
     {
-      "epoch": 0.57,
-      "learning_rate": 0.00014271844660194175,
-      "loss": 2.0834,
+      "epoch": 0.2,
+      "learning_rate": 0.00015945017182130585,
+      "loss": 2.1134,
       "step": 59
     },
     {
-      "epoch": 0.58,
-      "learning_rate": 0.000141747572815534,
-      "loss": 2.0255,
+      "epoch": 0.21,
+      "learning_rate": 0.00015876288659793814,
+      "loss": 2.1652,
       "step": 60
     },
     {
-      "epoch": 0.59,
-      "learning_rate": 0.00014077669902912623,
-      "loss": 2.131,
+      "epoch": 0.21,
+      "learning_rate": 0.00015807560137457046,
+      "loss": 2.0051,
       "step": 61
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 0.00013980582524271846,
-      "loss": 2.2428,
+      "epoch": 0.21,
+      "learning_rate": 0.00015738831615120274,
+      "loss": 2.0604,
       "step": 62
     },
     {
-      "epoch": 0.61,
-      "learning_rate": 0.0001388349514563107,
-      "loss": 2.0831,
+      "epoch": 0.22,
+      "learning_rate": 0.00015670103092783506,
+      "loss": 2.1708,
       "step": 63
     },
     {
-      "epoch": 0.62,
-      "learning_rate": 0.00013786407766990292,
-      "loss": 2.1633,
+      "epoch": 0.22,
+      "learning_rate": 0.00015601374570446737,
+      "loss": 2.1106,
       "step": 64
     },
     {
-      "epoch": 0.63,
-      "learning_rate": 0.00013689320388349515,
-      "loss": 2.2224,
+      "epoch": 0.22,
+      "learning_rate": 0.00015532646048109966,
+      "loss": 2.1445,
       "step": 65
     },
     {
-      "epoch": 0.64,
-      "learning_rate": 0.0001359223300970874,
-      "loss": 2.0999,
+      "epoch": 0.23,
+      "learning_rate": 0.00015463917525773197,
+      "loss": 2.0879,
       "step": 66
     },
     {
-      "epoch": 0.65,
-      "learning_rate": 0.00013495145631067963,
-      "loss": 2.1749,
+      "epoch": 0.23,
+      "learning_rate": 0.0001539518900343643,
+      "loss": 2.1498,
       "step": 67
     },
     {
-      "epoch": 0.65,
-      "learning_rate": 0.00013398058252427186,
-      "loss": 1.9726,
+      "epoch": 0.23,
+      "learning_rate": 0.00015326460481099657,
+      "loss": 2.0719,
       "step": 68
     },
     {
-      "epoch": 0.66,
-      "learning_rate": 0.0001330097087378641,
-      "loss": 2.1678,
+      "epoch": 0.24,
+      "learning_rate": 0.00015257731958762886,
+      "loss": 2.2167,
       "step": 69
     },
     {
-      "epoch": 0.67,
-      "learning_rate": 0.00013203883495145632,
-      "loss": 2.0646,
+      "epoch": 0.24,
+      "learning_rate": 0.00015189003436426118,
+      "loss": 2.0811,
       "step": 70
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 0.00013106796116504855,
-      "loss": 2.0049,
+      "epoch": 0.24,
+      "learning_rate": 0.00015120274914089346,
+      "loss": 2.1058,
       "step": 71
     },
     {
-      "epoch": 0.69,
-      "learning_rate": 0.00013009708737864078,
-      "loss": 2.0944,
+      "epoch": 0.25,
+      "learning_rate": 0.00015051546391752578,
+      "loss": 2.0392,
       "step": 72
     },
     {
-      "epoch": 0.7,
-      "learning_rate": 0.00012912621359223304,
-      "loss": 2.2013,
+      "epoch": 0.25,
+      "learning_rate": 0.0001498281786941581,
+      "loss": 2.0957,
       "step": 73
     },
     {
-      "epoch": 0.71,
-      "learning_rate": 0.00012815533980582526,
-      "loss": 2.311,
+      "epoch": 0.25,
+      "learning_rate": 0.00014914089347079038,
+      "loss": 1.9994,
       "step": 74
     },
     {
-      "epoch": 0.72,
-      "learning_rate": 0.0001271844660194175,
-      "loss": 2.0863,
+      "epoch": 0.26,
+      "learning_rate": 0.0001484536082474227,
+      "loss": 2.0464,
       "step": 75
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 0.00012621359223300972,
-      "loss": 2.2028,
+      "epoch": 0.26,
+      "learning_rate": 0.000147766323024055,
+      "loss": 2.0417,
       "step": 76
     },
     {
-      "epoch": 0.74,
-      "learning_rate": 0.00012524271844660195,
-      "loss": 2.0283,
+      "epoch": 0.26,
+      "learning_rate": 0.0001470790378006873,
+      "loss": 2.105,
       "step": 77
     },
     {
-      "epoch": 0.75,
-      "learning_rate": 0.00012427184466019418,
-      "loss": 2.2133,
+      "epoch": 0.27,
+      "learning_rate": 0.00014639175257731958,
+      "loss": 2.1147,
       "step": 78
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 0.0001233009708737864,
-      "loss": 2.1084,
+      "epoch": 0.27,
+      "learning_rate": 0.0001457044673539519,
+      "loss": 1.9964,
       "step": 79
     },
     {
-      "epoch": 0.77,
-      "learning_rate": 0.00012233009708737864,
-      "loss": 1.967,
+      "epoch": 0.27,
+      "learning_rate": 0.00014501718213058418,
+      "loss": 1.9723,
       "step": 80
     },
     {
-      "epoch": 0.78,
-      "learning_rate": 0.00012135922330097087,
-      "loss": 2.3109,
+      "epoch": 0.28,
+      "learning_rate": 0.0001443298969072165,
+      "loss": 2.0621,
       "step": 81
     },
     {
-      "epoch": 0.79,
-      "learning_rate": 0.0001203883495145631,
-      "loss": 2.2248,
+      "epoch": 0.28,
+      "learning_rate": 0.00014364261168384881,
+      "loss": 2.2703,
       "step": 82
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.00011941747572815534,
-      "loss": 2.1178,
+      "epoch": 0.28,
+      "learning_rate": 0.0001429553264604811,
+      "loss": 2.0815,
       "step": 83
     },
     {
-      "epoch": 0.81,
-      "learning_rate": 0.00011844660194174757,
-      "loss": 2.161,
+      "epoch": 0.29,
+      "learning_rate": 0.00014226804123711342,
+      "loss": 2.0774,
       "step": 84
     },
     {
-      "epoch": 0.82,
-      "learning_rate": 0.0001174757281553398,
-      "loss": 2.0778,
+      "epoch": 0.29,
+      "learning_rate": 0.00014158075601374573,
+      "loss": 2.066,
       "step": 85
     },
     {
-      "epoch": 0.83,
-      "learning_rate": 0.00011650485436893204,
-      "loss": 2.2326,
+      "epoch": 0.29,
+      "learning_rate": 0.00014089347079037802,
+      "loss": 2.03,
       "step": 86
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.00011553398058252427,
-      "loss": 2.0262,
+      "epoch": 0.3,
+      "learning_rate": 0.0001402061855670103,
+      "loss": 2.1433,
       "step": 87
     },
     {
-      "epoch": 0.85,
-      "learning_rate": 0.0001145631067961165,
-      "loss": 2.076,
+      "epoch": 0.3,
+      "learning_rate": 0.00013951890034364262,
+      "loss": 2.0811,
       "step": 88
     },
     {
-      "epoch": 0.86,
-      "learning_rate": 0.00011359223300970874,
-      "loss": 2.0044,
+      "epoch": 0.31,
+      "learning_rate": 0.0001388316151202749,
+      "loss": 1.9791,
       "step": 89
     },
     {
-      "epoch": 0.87,
-      "learning_rate": 0.00011262135922330097,
-      "loss": 2.0397,
+      "epoch": 0.31,
+      "learning_rate": 0.00013814432989690722,
+      "loss": 2.0876,
       "step": 90
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.0001116504854368932,
-      "loss": 2.1135,
+      "epoch": 0.31,
+      "learning_rate": 0.00013745704467353953,
+      "loss": 2.0314,
       "step": 91
     },
     {
-      "epoch": 0.89,
-      "learning_rate": 0.00011067961165048544,
-      "loss": 2.29,
+      "epoch": 0.32,
+      "learning_rate": 0.00013676975945017182,
+      "loss": 1.9485,
       "step": 92
     },
     {
-      "epoch": 0.9,
-      "learning_rate": 0.00010970873786407767,
-      "loss": 1.949,
+      "epoch": 0.32,
+      "learning_rate": 0.00013608247422680414,
+      "loss": 2.078,
       "step": 93
     },
     {
-      "epoch": 0.9,
-      "learning_rate": 0.0001087378640776699,
-      "loss": 2.1177,
+      "epoch": 0.32,
+      "learning_rate": 0.00013539518900343645,
+      "loss": 2.1251,
       "step": 94
     },
     {
-      "epoch": 0.91,
-      "learning_rate": 0.00010776699029126213,
-      "loss": 2.1405,
+      "epoch": 0.33,
+      "learning_rate": 0.00013470790378006874,
+      "loss": 1.9736,
       "step": 95
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.00010679611650485437,
-      "loss": 2.2089,
+      "epoch": 0.33,
+      "learning_rate": 0.00013402061855670103,
+      "loss": 2.0189,
       "step": 96
     },
     {
-      "epoch": 0.93,
-      "learning_rate": 0.0001058252427184466,
-      "loss": 2.1267,
+      "epoch": 0.33,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 2.0061,
       "step": 97
     },
     {
-      "epoch": 0.94,
-      "learning_rate": 0.00010485436893203883,
-      "loss": 2.0522,
+      "epoch": 0.34,
+      "learning_rate": 0.00013264604810996563,
+      "loss": 1.9595,
       "step": 98
     },
     {
-      "epoch": 0.95,
-      "learning_rate": 0.00010388349514563107,
-      "loss": 2.0273,
+      "epoch": 0.34,
+      "learning_rate": 0.00013195876288659794,
+      "loss": 1.9702,
       "step": 99
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 0.0001029126213592233,
-      "loss": 2.1042,
+      "epoch": 0.34,
+      "learning_rate": 0.00013127147766323026,
+      "loss": 2.0322,
       "step": 100
     }
   ],
   "logging_steps": 1,
-  "max_steps": 206,
-  "num_train_epochs": 2,
+  "max_steps": 291,
+  "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 2.9528801422848e+16,
+  "total_flos": 6.083398113601536e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c85ca10d57026468ea370fc1e96b5bd54f01f7c7e107e8275fff6dab39b89727
+oid sha256:7e3410eea0ea0eb09ca576511099334880accaab360c0279f3099c9e4d2e877a
 size 4027