Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b047a0e786eb1d688011b6ef8ace7e38cf8666e860bf3a1d20a6db01c28377e
+oid sha256:f7c9c6832d9b9ae653131500755efe8459dc2939032a1a72e8b52c63f0712a9c
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5493e50fc6dd02e0330bd689be29ebdf17ddd1e1450ea8d752f0381e29d578
+oid sha256:261006764b961cb77ecaa2b21e3d80eafad77c93a3fcd0f268ba14b40110edb0
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb53e956d37160bedc46d0adb3a1f88aaddc065e5d5a137bf434121ef2313991
+oid sha256:7ed2b6db1ec60a90525d794c2133b0b06d86cdbb9449fa71c4bc4c94c91b3cb8
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8d82f2b63956f7a657676c6c14dd16c65381bf4daf3a0e2823620944d3d859
+oid sha256:ce8670e31cae653a7a564e9213a3ea8b6e626fad48fd45659de57f0263ddc216
 size 1465

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6247be075973430c70e5980bd5af624466882ca896e8994078f6707661e890ca
+oid sha256:9af54fe549c06785a9c79eaa3f0c67144a19c56e1370229244d49c8a22fcaaec
 size 17082898

last-checkpoint/tokenizer_config.json

@@ -47,7 +47,7 @@
   "eos_token": "</s>",
   "extra_special_tokens": {},
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "model_max_length": 120,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},

last-checkpoint/trainer_state.json

@@ -1,49 +1,115 @@
 {
   "best_global_step": null,
-  "best_metric": null,
+  "best_metric": Infinity,
   "best_model_checkpoint": null,
-  "epoch": 0.0025186379206125326,
+  "epoch": 0.12690355329949238,
   "eval_steps": 1000,
-  "global_step": 200,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0006296594801531332,
-      "grad_norm": 8.148825645446777,
-      "learning_rate": 4.99691466854725e-05,
-      "loss": 8.805,
-      "step": 50
+      "epoch": 0.0001269035532994924,
+      "grad_norm": 22.005727767944336,
+      "learning_rate": 0.0,
+      "loss": 13.3757,
+      "step": 1
     },
     {
-      "epoch": 0.0012593189603062663,
-      "grad_norm": 9.406821250915527,
-      "learning_rate": 4.993766371146484e-05,
-      "loss": 7.6597,
+      "epoch": 0.012690355329949238,
+      "grad_norm": 38.664306640625,
+      "learning_rate": 1.2563451776649746e-05,
+      "loss": 11.1669,
       "step": 100
     },
     {
-      "epoch": 0.0018889784404593996,
-      "grad_norm": 12.482063293457031,
-      "learning_rate": 4.9906180737457186e-05,
-      "loss": 7.2093,
-      "step": 150
+      "epoch": 0.025380710659898477,
+      "grad_norm": 25.380781173706055,
+      "learning_rate": 2.5253807106598986e-05,
+      "loss": 7.8049,
+      "step": 200
     },
     {
-      "epoch": 0.0025186379206125326,
-      "grad_norm": 15.39159870147705,
-      "learning_rate": 4.987469776344953e-05,
-      "loss": 6.813,
-      "step": 200
+      "epoch": 0.03807106598984772,
+      "grad_norm": 25.609392166137695,
+      "learning_rate": 3.794416243654822e-05,
+      "loss": 6.6303,
+      "step": 300
+    },
+    {
+      "epoch": 0.050761421319796954,
+      "grad_norm": 21.906394958496094,
+      "learning_rate": 5.063451776649747e-05,
+      "loss": 5.6649,
+      "step": 400
+    },
+    {
+      "epoch": 0.06345177664974619,
+      "grad_norm": 13.918214797973633,
+      "learning_rate": 6.33248730964467e-05,
+      "loss": 4.9902,
+      "step": 500
+    },
+    {
+      "epoch": 0.07614213197969544,
+      "grad_norm": 10.558023452758789,
+      "learning_rate": 7.601522842639595e-05,
+      "loss": 4.5313,
+      "step": 600
+    },
+    {
+      "epoch": 0.08883248730964467,
+      "grad_norm": 9.60472297668457,
+      "learning_rate": 8.870558375634518e-05,
+      "loss": 4.2284,
+      "step": 700
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 10.893503189086914,
+      "learning_rate": 9.992652952177398e-05,
+      "loss": 3.9399,
+      "step": 800
+    },
+    {
+      "epoch": 0.11421319796954314,
+      "grad_norm": 10.343321800231934,
+      "learning_rate": 9.92586160833556e-05,
+      "loss": 3.6866,
+      "step": 900
+    },
+    {
+      "epoch": 0.12690355329949238,
+      "grad_norm": 10.732213020324707,
+      "learning_rate": 9.859070264493722e-05,
+      "loss": 3.5191,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12690355329949238,
+      "eval_loss": NaN,
+      "eval_runtime": 758.7504,
+      "eval_samples_per_second": 332.374,
+      "eval_steps_per_second": 41.547,
+      "step": 1000
     }
   ],
-  "logging_steps": 50,
-  "max_steps": 79408,
+  "logging_steps": 100,
+  "max_steps": 15760,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 200,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
   "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
     "TrainerControl": {
       "args": {
         "should_epoch_stop": false,
@@ -55,8 +121,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 62742348630528.0,
-  "train_batch_size": 16,
+  "total_flos": 542189854973952.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba024ed71d2a66548909fa4f3d039c74313393df3397391d5c42a5b3a406964
+oid sha256:3d31271322373138a24b0926f70a31fa802fc9dad83a42bf09bcb1e65b34018c
 size 5841