Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64fce98847974a1fbc15a5211620e911f29d0a6fa5bc6a5bf2e0acabc13c361
+oid sha256:d1992bc8cbd8cfc6c88b1963eedb9aa5c6b4583be00c396662c3f6a358ddb1ad
 size 268290900

run-0/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5093cae8988b1c78fe1fa0de0ab86a02d9feb54f3792947511ec2b5b40b1b9
+oid sha256:2a6bfc0d04fa062aafe14fdad65aae2ea6adae5c8469541e9b7863a1faad3e9a
 size 268290900

run-0/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622dd8e8d3db209abf2f42558ee6274e310b285bed8f6aed6ce69d0a4ffe7804
+oid sha256:80c0e2557f9299a203cad2cf29f7a6e92288b2b70263361fd6952fed79531eed
 size 536643898

run-0/checkpoint-1000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae8803a4cfd93a17b836d411a0cdc283947bea33521d8af530f6f31af83987d
+oid sha256:c35ee7e612988cfbcef57649260f5e638d50749c336bb364c0aaa11036e867c9
 size 14244

run-0/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045cf4abe065257226fe11ac1a91dfd4c5b953cb2366365ef8bb18b4cf33e734
+oid sha256:ed9da1cbe846856af516cf037dd225e7f48e2737ef84c42a9bee0753b8c140ef
 size 1064

run-0/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128e3e531e1f78b4508e424d6b0320b2ccd0b6f2b6fb1f09e3f886f07d5e86ea
-size 4728
+oid sha256:3995b387f2d0291be709cdbf61f96ec0665c9f1f556146e986cb9b22d69b84bd
+size 5176

run-0/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44956ed874cfbe79d37340b63ddbcd7fbdb99066767991fce3541b8cc0896627
+oid sha256:c12548a0e1d2999b1e89a6451858c1ba19278e932f73f0ec0a958da3b98809ec
 size 268290900

run-0/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b6101a5040379ef3c94acbc4c966b58cc6632daaa26d4c3194914127aa06d2
+oid sha256:e508a0180bc2432169987e3671ecfea4c7f7399055995ca577258a0697775a3d
 size 536643898

run-0/checkpoint-1500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4150b40cdd095f99e6d506db714a6c0a9a316d6b4d021acbfec8d198c96919
+oid sha256:1c10319269a5ccb2640eed78049edda0fca1ea40d757f64b6ab5474fe9e926f9
 size 14244

run-0/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7b4645e59a5c5cb66f63e8bcb5f006c535fd0ea63db9ae152dd586fd465b28
+oid sha256:ad4d7d251acf36e559c362893a1fb310c9f46b20e8a330025a14b6829ce4ab07
 size 1064

run-0/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128e3e531e1f78b4508e424d6b0320b2ccd0b6f2b6fb1f09e3f886f07d5e86ea
-size 4728
+oid sha256:3995b387f2d0291be709cdbf61f96ec0665c9f1f556146e986cb9b22d69b84bd
+size 5176

run-0/checkpoint-2000/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.41.1",
   "vocab_size": 30522
 }

run-0/checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156ea8881e640a983d137bf9a2f1b9c9831f3dfa43621563d93e76d3f69fdeaf
+oid sha256:fc630be871e84a2ba797e4b734dafee8fd052aad75df18916397c3c502e9da12
 size 268290900

run-0/checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ca37818535a2f93dc324d93af207b76fd7f6a13a57ff3d91993e4069599c7f
+oid sha256:c6f651cfe4ff9f8d1c3b71bb6d9d942ddaabbc951698f633c577cf1fddc8aaa6
 size 536643898

run-0/checkpoint-2000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5613af56824b89d2251abc079d69f51d9497a128212db6eb459f4c957e78a29b
+oid sha256:37ccc14cc902672c3d8e770c2a2ce3a532b454981f3118cb18a09274102a99fc
 size 14244

run-0/checkpoint-2000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf6d4c2c13eda2c2dfacdbfc8684055c5603a92b6c0c386d7c757b108195d12
+oid sha256:f38866eaf1d2baeb52a55cb38ece6ee67f3213265b0830dd06c82a9148795bea
 size 1064

run-0/checkpoint-2000/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-0/checkpoint-2000/trainer_state.json

@@ -10,94 +10,110 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5958064516129032,
-      "eval_loss": 0.1949465274810791,
-      "eval_runtime": 1.357,
-      "eval_samples_per_second": 2284.501,
-      "eval_steps_per_second": 47.901,
+      "eval_accuracy": 0.6674193548387096,
+      "eval_loss": 0.416048139333725,
+      "eval_runtime": 1.3187,
+      "eval_samples_per_second": 2350.748,
+      "eval_steps_per_second": 49.29,
       "step": 318
     },
     {
-      "epoch": 1.57,
-      "learning_rate": 1.606918238993711e-05,
-      "loss": 0.3113,
+      "epoch": 1.5723270440251573,
+      "grad_norm": 0.9905994534492493,
+      "learning_rate": 1.550763701707098e-05,
+      "loss": 0.6477,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8164516129032258,
-      "eval_loss": 0.09700000286102295,
-      "eval_runtime": 1.3602,
-      "eval_samples_per_second": 2279.158,
-      "eval_steps_per_second": 47.789,
+      "eval_accuracy": 0.8332258064516129,
+      "eval_loss": 0.15088918805122375,
+      "eval_runtime": 1.3272,
+      "eval_samples_per_second": 2335.773,
+      "eval_steps_per_second": 48.976,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8754838709677419,
-      "eval_loss": 0.0647290050983429,
-      "eval_runtime": 1.3748,
-      "eval_samples_per_second": 2254.826,
-      "eval_steps_per_second": 47.279,
+      "eval_accuracy": 0.886774193548387,
+      "eval_loss": 0.07951628416776657,
+      "eval_runtime": 1.3591,
+      "eval_samples_per_second": 2280.965,
+      "eval_steps_per_second": 47.827,
       "step": 954
     },
     {
-      "epoch": 3.14,
-      "learning_rate": 1.2138364779874214e-05,
-      "loss": 0.1105,
+      "epoch": 3.1446540880503147,
+      "grad_norm": 0.7344270348548889,
+      "learning_rate": 1.101527403414196e-05,
+      "loss": 0.1749,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8951612903225806,
-      "eval_loss": 0.05031874030828476,
-      "eval_runtime": 1.3686,
-      "eval_samples_per_second": 2265.046,
-      "eval_steps_per_second": 47.493,
+      "eval_accuracy": 0.9090322580645162,
+      "eval_loss": 0.05769029259681702,
+      "eval_runtime": 1.3435,
+      "eval_samples_per_second": 2307.35,
+      "eval_steps_per_second": 48.38,
       "step": 1272
     },
     {
-      "epoch": 4.72,
-      "learning_rate": 8.207547169811321e-06,
-      "loss": 0.0722,
+      "epoch": 4.716981132075472,
+      "grad_norm": 0.4701627790927887,
+      "learning_rate": 6.522911051212939e-06,
+      "loss": 0.0902,
       "step": 1500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9035483870967742,
-      "eval_loss": 0.04259829595685005,
-      "eval_runtime": 1.3733,
-      "eval_samples_per_second": 2257.258,
-      "eval_steps_per_second": 47.33,
+      "eval_accuracy": 0.9193548387096774,
+      "eval_loss": 0.04808399826288223,
+      "eval_runtime": 1.3493,
+      "eval_samples_per_second": 2297.566,
+      "eval_steps_per_second": 48.175,
       "step": 1590
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.91,
-      "eval_loss": 0.03827530890703201,
-      "eval_runtime": 1.3751,
-      "eval_samples_per_second": 2254.357,
-      "eval_steps_per_second": 47.269,
+      "eval_accuracy": 0.9235483870967742,
+      "eval_loss": 0.0440458320081234,
+      "eval_runtime": 1.3465,
+      "eval_samples_per_second": 2302.187,
+      "eval_steps_per_second": 48.272,
       "step": 1908
     },
     {
-      "epoch": 6.29,
-      "learning_rate": 4.276729559748428e-06,
-      "loss": 0.058,
+      "epoch": 6.289308176100629,
+      "grad_norm": 0.4379720985889435,
+      "learning_rate": 2.0305480682839176e-06,
+      "loss": 0.0704,
       "step": 2000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2544,
+  "max_steps": 2226,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 7,
   "save_steps": 500,
-  "total_flos": 519271419317532.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 520991326672152.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.05314446157998587,
-    "num_train_epochs": 8,
-    "temperature": 17
+    "alpha": 0.5999229797501479,
+    "num_train_epochs": 7,
+    "temperature": 2
   }
 }

run-0/checkpoint-2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128e3e531e1f78b4508e424d6b0320b2ccd0b6f2b6fb1f09e3f886f07d5e86ea
-size 4728
+oid sha256:3995b387f2d0291be709cdbf61f96ec0665c9f1f556146e986cb9b22d69b84bd
+size 5176

run-1/checkpoint-1000/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.41.1",
   "vocab_size": 30522
 }

run-1/checkpoint-1000/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-1/checkpoint-1000/trainer_state.json

@@ -10,55 +10,69 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5896774193548387,
-      "eval_loss": 0.21174675226211548,
-      "eval_runtime": 1.3562,
-      "eval_samples_per_second": 2285.793,
-      "eval_steps_per_second": 47.928,
+      "eval_accuracy": 0.577741935483871,
+      "eval_loss": 0.20344002544879913,
+      "eval_runtime": 1.3567,
+      "eval_samples_per_second": 2284.973,
+      "eval_steps_per_second": 47.911,
       "step": 318
     },
     {
-      "epoch": 1.57,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3315,
+      "epoch": 1.5723270440251573,
+      "grad_norm": 0.494202196598053,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3218,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8035483870967742,
-      "eval_loss": 0.10993191599845886,
-      "eval_runtime": 1.3614,
-      "eval_samples_per_second": 2277.03,
-      "eval_steps_per_second": 47.744,
+      "eval_accuracy": 0.8129032258064516,
+      "eval_loss": 0.10371456295251846,
+      "eval_runtime": 1.3471,
+      "eval_samples_per_second": 2301.291,
+      "eval_steps_per_second": 48.253,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8616129032258064,
-      "eval_loss": 0.07778050750494003,
-      "eval_runtime": 1.3633,
-      "eval_samples_per_second": 2273.815,
-      "eval_steps_per_second": 47.677,
+      "eval_accuracy": 0.8709677419354839,
+      "eval_loss": 0.07233396172523499,
+      "eval_runtime": 1.3503,
+      "eval_samples_per_second": 2295.728,
+      "eval_steps_per_second": 48.136,
       "step": 954
     },
     {
-      "epoch": 3.14,
-      "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1256,
+      "epoch": 3.1446540880503147,
+      "grad_norm": 0.4743537902832031,
+      "learning_rate": 9.517819706498952e-06,
+      "loss": 0.1194,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 1908,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 259991364709020.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 260941334653608.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8444910353259852,
-    "num_train_epochs": 5,
-    "temperature": 10
+    "alpha": 0.6325268278134527,
+    "num_train_epochs": 6,
+    "temperature": 12
   }
 }

run-1/checkpoint-1500/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.41.1",
   "vocab_size": 30522
 }

run-1/checkpoint-1500/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-1/checkpoint-1500/trainer_state.json

@@ -10,70 +10,85 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5896774193548387,
-      "eval_loss": 0.21174675226211548,
-      "eval_runtime": 1.3562,
-      "eval_samples_per_second": 2285.793,
-      "eval_steps_per_second": 47.928,
+      "eval_accuracy": 0.577741935483871,
+      "eval_loss": 0.20344002544879913,
+      "eval_runtime": 1.3567,
+      "eval_samples_per_second": 2284.973,
+      "eval_steps_per_second": 47.911,
       "step": 318
     },
     {
-      "epoch": 1.57,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3315,
+      "epoch": 1.5723270440251573,
+      "grad_norm": 0.494202196598053,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3218,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8035483870967742,
-      "eval_loss": 0.10993191599845886,
-      "eval_runtime": 1.3614,
-      "eval_samples_per_second": 2277.03,
-      "eval_steps_per_second": 47.744,
+      "eval_accuracy": 0.8129032258064516,
+      "eval_loss": 0.10371456295251846,
+      "eval_runtime": 1.3471,
+      "eval_samples_per_second": 2301.291,
+      "eval_steps_per_second": 48.253,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8616129032258064,
-      "eval_loss": 0.07778050750494003,
-      "eval_runtime": 1.3633,
-      "eval_samples_per_second": 2273.815,
-      "eval_steps_per_second": 47.677,
+      "eval_accuracy": 0.8709677419354839,
+      "eval_loss": 0.07233396172523499,
+      "eval_runtime": 1.3503,
+      "eval_samples_per_second": 2295.728,
+      "eval_steps_per_second": 48.136,
       "step": 954
     },
     {
-      "epoch": 3.14,
-      "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1256,
+      "epoch": 3.1446540880503147,
+      "grad_norm": 0.4743537902832031,
+      "learning_rate": 9.517819706498952e-06,
+      "loss": 0.1194,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8783870967741936,
-      "eval_loss": 0.06527664512395859,
-      "eval_runtime": 1.3774,
-      "eval_samples_per_second": 2250.621,
-      "eval_steps_per_second": 47.19,
+      "eval_accuracy": 0.8848387096774194,
+      "eval_loss": 0.05824179947376251,
+      "eval_runtime": 1.3553,
+      "eval_samples_per_second": 2287.256,
+      "eval_steps_per_second": 47.959,
       "step": 1272
     },
     {
-      "epoch": 4.72,
-      "learning_rate": 1.1320754716981133e-06,
-      "loss": 0.0903,
+      "epoch": 4.716981132075472,
+      "grad_norm": 0.3467690646648407,
+      "learning_rate": 4.276729559748428e-06,
+      "loss": 0.0813,
       "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 1908,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 390310534917408.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 391368939443328.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8444910353259852,
-    "num_train_epochs": 5,
-    "temperature": 10
+    "alpha": 0.6325268278134527,
+    "num_train_epochs": 6,
+    "temperature": 12
   }
 }

run-1/checkpoint-500/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.41.1",
   "vocab_size": 30522
 }

run-1/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd3bf3d49936dfd8baa9582c8eaba7717d92d7d1f8d94038d4151e4c2d4f278
+oid sha256:d1992bc8cbd8cfc6c88b1963eedb9aa5c6b4583be00c396662c3f6a358ddb1ad
 size 268290900

run-1/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a7b2cb6089e0574b3e01b3ab3738f4f73b1a92359ec8127a9ce373bb97a274
+oid sha256:569559a6c1c61ada1010013edab7b010346f26be17388bea8473982069d749b5
 size 536643898

run-1/checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8174c1d6ac2627de77161655e4e20ef37d9f2235e2e7c4adc0da0d4e0e14b6d
+oid sha256:b9fb2a0dfb1b0ccef3590fe01e9bd16b6db86f247cc9c7e77290c217a53bac20
 size 14244

run-1/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1264523e958cf7990dc5f42d876cc12129475c4603804cf66868aaf25c2c24
+oid sha256:bb78b1e790f49c38375a9a03add3c9373ef72cf0138709ffb96775535ef084c6
 size 1064

run-1/checkpoint-500/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-1/checkpoint-500/trainer_state.json

@@ -10,31 +10,44 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5896774193548387,
-      "eval_loss": 0.21174675226211548,
-      "eval_runtime": 1.3562,
-      "eval_samples_per_second": 2285.793,
-      "eval_steps_per_second": 47.928,
+      "eval_accuracy": 0.577741935483871,
+      "eval_loss": 0.20344002544879913,
+      "eval_runtime": 1.3567,
+      "eval_samples_per_second": 2284.973,
+      "eval_steps_per_second": 47.911,
       "step": 318
     },
     {
-      "epoch": 1.57,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3315,
+      "epoch": 1.5723270440251573,
+      "grad_norm": 0.494202196598053,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3218,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 1908,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 129219778448376.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 130072209152340.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8444910353259852,
-    "num_train_epochs": 5,
-    "temperature": 10
+    "alpha": 0.6325268278134527,
+    "num_train_epochs": 6,
+    "temperature": 12
   }
 }

run-1/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440b33c1d4af396a1f83c40460d843946c313509afa8ac95fbf678728a7e05c7
-size 4728
+oid sha256:720882e08adee18bc186850828f02514ae1f0c4061921a151ad1b71291c1e3c8
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3995b387f2d0291be709cdbf61f96ec0665c9f1f556146e986cb9b22d69b84bd
+oid sha256:720882e08adee18bc186850828f02514ae1f0c4061921a151ad1b71291c1e3c8
 size 5176