Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0456fc474fab29fc0ec8abc6204bd83607d73963771a41bab0df44c7115542b
+oid sha256:13a6300c6c39b121f94d275c2c2a549c2c8ae61e533c269f2d4e6d11187a0ec4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8890ebf1fefd043e0366a59d2a24c540b88f0ff1d65428a210bf3560c3e4bd69
+oid sha256:91f1f9608b67ba55573445bc2166dc2391702aeb4acd1bbe8648dc3e1919b61a
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a1d0fa3c6d845cfcdb586fc5456e69f414fd350362eb5b418907a512e6ec4c
+oid sha256:db6358da13f324834878bd2b4485e5667664a0d92ed16a7f6a761dd9dea8cc65
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 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": 2.326402187347412,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 2.451620578765869,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,191 +11,107 @@
     {
       "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,
+      "loss": 2.5383,
       "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,
+      "eval_loss": 2.5257716178894043,
+      "eval_runtime": 206.1349,
+      "eval_samples_per_second": 30.436,
+      "eval_steps_per_second": 3.808,
       "step": 400
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 2.4946,
+      "loss": 2.4959,
       "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,
+      "eval_loss": 2.5014102458953857,
+      "eval_runtime": 282.6461,
+      "eval_samples_per_second": 22.197,
+      "eval_steps_per_second": 2.777,
       "step": 500
     },
     {
       "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 2.4686,
+      "loss": 2.4693,
       "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,
+      "eval_loss": 2.475057601928711,
+      "eval_runtime": 205.7759,
+      "eval_samples_per_second": 30.489,
+      "eval_steps_per_second": 3.815,
       "step": 600
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.4503,
+      "loss": 2.4523,
       "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,
+      "eval_loss": 2.451620578765869,
+      "eval_runtime": 322.0554,
+      "eval_samples_per_second": 19.481,
+      "eval_steps_per_second": 2.437,
       "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": 3.792256256581632e+16,
+  "total_flos": 2.042513200078848e+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:faed5845c6fa602a9a75d6d7a3c4d37017580998e72f3835a07c1c95f579635b
+oid sha256:6a0ffd8c2b139f27950886c21bfa338a00634210331df117dcff8cd3df7ce8ad
 size 4219