Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87eeecbbab6cd96154d268f70f957ad246d6273e5551f07a15a785a67b6e5e98
+oid sha256:2e6c7ce88e2275574e4d7579694f1859b5baaf1088f8c79b8f33ec9ddb0d5620
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe6c1069872dfe0588f0180a743c9d3c5a2d88acb932323967c50591a7e2d59
+oid sha256:91f7d8a4cd06a8968112b3a3c64dedc9f17dbff63bf85caeca697bde33e97bf6
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2584adcfe5878130368943010052e98d7f9569785b451bb350577d373a1f2f
+oid sha256:b26837cce4b9686e80c01fd503576bec322032548fab3bb432c6bb17f35ea1da
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
-size 14500569
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.401764154434204,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 0.6557377049180327,
+  "best_metric": 2.5578970909118652,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,135 +11,51 @@
     {
       "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 2.7399,
+      "loss": 2.7401,
       "step": 100
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6418099403381348,
-      "eval_runtime": 347.6157,
-      "eval_samples_per_second": 18.049,
-      "eval_steps_per_second": 2.258,
+      "eval_loss": 2.6424810886383057,
+      "eval_runtime": 206.4108,
+      "eval_samples_per_second": 30.396,
+      "eval_steps_per_second": 3.803,
       "step": 100
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 2.6052,
+      "loss": 2.6061,
       "step": 200
     },
     {
       "epoch": 0.15,
-      "eval_loss": 2.5918312072753906,
-      "eval_runtime": 333.731,
-      "eval_samples_per_second": 18.8,
-      "eval_steps_per_second": 2.352,
+      "eval_loss": 2.5929574966430664,
+      "eval_runtime": 206.2177,
+      "eval_samples_per_second": 30.424,
+      "eval_steps_per_second": 3.807,
       "step": 200
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.5622,
+      "loss": 2.5643,
       "step": 300
     },
     {
       "epoch": 0.22,
-      "eval_loss": 2.551574468612671,
-      "eval_runtime": 204.9306,
-      "eval_samples_per_second": 30.615,
-      "eval_steps_per_second": 3.831,
+      "eval_loss": 2.5578970909118652,
+      "eval_runtime": 206.509,
+      "eval_samples_per_second": 30.381,
+      "eval_steps_per_second": 3.801,
       "step": 300
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.0002,
-      "loss": 2.5366,
-      "step": 400
-    },
-    {
-      "epoch": 0.29,
-      "eval_loss": 2.517575263977051,
-      "eval_runtime": 204.3925,
-      "eval_samples_per_second": 30.696,
-      "eval_steps_per_second": 3.841,
-      "step": 400
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.0002,
-      "loss": 2.4946,
-      "step": 500
-    },
-    {
-      "epoch": 0.36,
-      "eval_loss": 2.4924821853637695,
-      "eval_runtime": 204.4035,
-      "eval_samples_per_second": 30.694,
-      "eval_steps_per_second": 3.84,
-      "step": 500
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.0002,
-      "loss": 2.4686,
-      "step": 600
-    },
-    {
-      "epoch": 0.44,
-      "eval_loss": 2.4666266441345215,
-      "eval_runtime": 207.3453,
-      "eval_samples_per_second": 30.259,
-      "eval_steps_per_second": 3.786,
-      "step": 600
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.0002,
-      "loss": 2.4503,
-      "step": 700
-    },
-    {
-      "epoch": 0.51,
-      "eval_loss": 2.4440107345581055,
-      "eval_runtime": 205.5485,
-      "eval_samples_per_second": 30.523,
-      "eval_steps_per_second": 3.819,
-      "step": 700
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0002,
-      "loss": 2.4271,
-      "step": 800
-    },
-    {
-      "epoch": 0.58,
-      "eval_loss": 2.4231719970703125,
-      "eval_runtime": 204.3763,
-      "eval_samples_per_second": 30.698,
-      "eval_steps_per_second": 3.841,
-      "step": 800
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.0002,
-      "loss": 2.3911,
-      "step": 900
-    },
-    {
-      "epoch": 0.66,
-      "eval_loss": 2.401764154434204,
-      "eval_runtime": 204.7042,
-      "eval_samples_per_second": 30.649,
-      "eval_steps_per_second": 3.835,
-      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.625477585518592e+16,
+  "total_flos": 8750270976491520.0,
   "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:faed5845c6fa602a9a75d6d7a3c4d37017580998e72f3835a07c1c95f579635b
+oid sha256:6a0ffd8c2b139f27950886c21bfa338a00634210331df117dcff8cd3df7ce8ad
 size 4219