Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f6516da94d5ec8ddf27952ae1e02036c6e994addf157282d37278175a4e61f
+oid sha256:074259398c315036a44af929ca38ebda5d87e484420b4ca7df775984005d0e84
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd857b4edc7c1663e4c8cee17ed70f733c5beb934d25ffdd5f745c3879f26c1
+oid sha256:108675afd3dfc8409d4b5347f8ed7d161c2f7f7f77850ebaf618e41ca9f06c6b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c7d9acd97a65ba6f52bddd9c1a7be0b5f95308e5fa05bcc7a62b6822eb6d6f
+oid sha256:cf02797a956bbc09d23fc6a6c1f3c0b3a9c44933f60941f080cf8bb2f9d1331d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 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": 2.5222103595733643,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 2.360255479812622,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 0.8014571948998178,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,65 +11,163 @@
     {
       "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": 2.4946,
+      "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
+    },
+    {
+      "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
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.167856193839104e+16,
+  "total_flos": 3.208363367473152e+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