Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18cfa0cde18cc61ddc1b0ddd2296f54b8b26eb7e3bcc3a4041c27e51f3a2ea71
+oid sha256:69041f32214c8333f95989146c92f75a08e5cbc350a6de5b44b932abdd1f9351
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00336005749bb34ab62ea72b8a9a675508379bbe1bad51806cddcab5abb66fd0
+oid sha256:7259a25650860d8bb8215f9796edd94667c2fd2ff8f4af3912ab231ded3d3fc3
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0990d8cdbc2bdd1880b9951298cbfae149ae47de29db9d5d340de0693addfd
+oid sha256:67bc3393a9340b81770a2f56f26e7c6954acce785b42d5c7c1a980acfd38e481
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/tokenizer.json

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

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4934604167938232,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 2.341019868850708,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 0.8743169398907104,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,79 +11,177 @@
     {
       "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 2.7406,
+      "loss": 2.7399,
       "step": 100
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6424405574798584,
-      "eval_runtime": 206.8728,
-      "eval_samples_per_second": 30.328,
-      "eval_steps_per_second": 3.795,
+      "eval_loss": 2.6418099403381348,
+      "eval_runtime": 347.6157,
+      "eval_samples_per_second": 18.049,
+      "eval_steps_per_second": 2.258,
       "step": 100
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 2.6056,
+      "loss": 2.6052,
       "step": 200
     },
     {
       "epoch": 0.15,
-      "eval_loss": 2.591430187225342,
-      "eval_runtime": 206.9647,
-      "eval_samples_per_second": 30.314,
-      "eval_steps_per_second": 3.793,
+      "eval_loss": 2.5918312072753906,
+      "eval_runtime": 333.731,
+      "eval_samples_per_second": 18.8,
+      "eval_steps_per_second": 2.352,
       "step": 200
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.5631,
+      "loss": 2.5622,
       "step": 300
     },
     {
       "epoch": 0.22,
-      "eval_loss": 2.5565075874328613,
-      "eval_runtime": 206.6263,
-      "eval_samples_per_second": 30.364,
-      "eval_steps_per_second": 3.799,
+      "eval_loss": 2.551574468612671,
+      "eval_runtime": 204.9306,
+      "eval_samples_per_second": 30.615,
+      "eval_steps_per_second": 3.831,
       "step": 300
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.5363,
+      "loss": 2.5366,
       "step": 400
     },
     {
       "epoch": 0.29,
-      "eval_loss": 2.5222103595733643,
-      "eval_runtime": 234.7988,
-      "eval_samples_per_second": 26.721,
-      "eval_steps_per_second": 3.343,
+      "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": 2.4935,
+      "loss": 2.4946,
       "step": 500
     },
     {
       "epoch": 0.36,
-      "eval_loss": 2.4934604167938232,
-      "eval_runtime": 206.7039,
-      "eval_samples_per_second": 30.353,
-      "eval_steps_per_second": 3.798,
+      "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
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 2.3881,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 2.3822004795074463,
+      "eval_runtime": 204.6048,
+      "eval_samples_per_second": 30.664,
+      "eval_steps_per_second": 3.837,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 2.3811,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 2.360255479812622,
+      "eval_runtime": 283.1616,
+      "eval_samples_per_second": 22.157,
+      "eval_steps_per_second": 2.772,
+      "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 2.3378,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 2.341019868850708,
+      "eval_runtime": 204.7618,
+      "eval_samples_per_second": 30.64,
+      "eval_steps_per_second": 3.834,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.459702746464256e+16,
+  "total_flos": 3.500881324867584e+16,
   "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:f6bbb4e93666410d7a938dd3851f7194e97be075889249a5ac42f4cb3cfacdd3
+oid sha256:faed5845c6fa602a9a75d6d7a3c4d37017580998e72f3835a07c1c95f579635b
 size 4219