Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde0c83fc1eeac95ffe9835a56ef9ccb6803b3787d581b43393869c98afa5d5b
+oid sha256:c0456fc474fab29fc0ec8abc6204bd83607d73963771a41bab0df44c7115542b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd65716521176dfab16b40c14cdca0cf667db2d43654d3c1b6b4bafd2e3b8294
+oid sha256:8890ebf1fefd043e0366a59d2a24c540b88f0ff1d65428a210bf3560c3e4bd69
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e1dc5f769c4cbaa0ba676908c39cfb7cd49352afc3941d90d0685280366309
+oid sha256:d4a1d0fa3c6d845cfcdb586fc5456e69f414fd350362eb5b418907a512e6ec4c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 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": 2.467857837677002,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.326402187347412,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,93 +11,191 @@
     {
       "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": 2.467,
+      "loss": 2.4686,
       "step": 600
     },
     {
       "epoch": 0.44,
-      "eval_loss": 2.467857837677002,
-      "eval_runtime": 287.8992,
-      "eval_samples_per_second": 21.792,
-      "eval_steps_per_second": 2.727,
+      "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
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 2.3496,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 2.326402187347412,
+      "eval_runtime": 365.7801,
+      "eval_samples_per_second": 17.152,
+      "eval_steps_per_second": 2.146,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.752346796949504e+16,
+  "total_flos": 3.792256256581632e+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