Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b356afc6d082488f2555ef406378069504708e31271d6e086beee3c91f1f5c83
+oid sha256:dd666fbb2e21f97e8d17488cc5d8a9b18c0a8214c01ae16975129e3ddda35428
 size 662430992

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b27e660c26757696366e20c37f079effc428107f2e9ffa74898f7f9b47361d
+oid sha256:0466bdd6ee79dd151ab52e97ce199c24b36d8ca9bc07fcc401488f453d1a5c9f
 size 674384884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63e25c94fd32bbfac74e77e235933e40e71931ccdab4688693badf62fc9d895
+oid sha256:7b4ffea7d126029ee70aa7566703f287532e95671ece76846e776643564a631e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d5a9f1444725574e6e96d7460d2ae867d4c9d4d70a147ad1691b8ce1c4b0b8
+oid sha256:d22d068494c14e8847a8db8a2ed0232120d3dfab2e76b5604ae0a39a1b140a25
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e844065e2ec1428132da97db98340b7020ef84b112f1abe984badffc1a1d8a
+oid sha256:90710af1ca4896b473e6e0eb3fbd88a6b938e5e7b17f9d85f7f48d00f56a79bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3774449d16a3fcd1d29aba215bc5841e6b8bc77f3a4c81e9a133c2a3c87bcc8d
+oid sha256:bcba06152d0f2be800761c223eaba18b4b433f1e651708bc3ad9af02ed0b3614
 size 15024

last-checkpoint/trainer_state.json

@@ -2,7 +2,7 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 14.285714285714286,
-  "eval_steps": 20,
+  "eval_steps": 200,
   "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -11,119 +11,79 @@
     {
       "epoch": 0.14285714285714285,
       "eval_loss": 3.078927516937256,
-      "eval_runtime": 4.9541,
-      "eval_samples_per_second": 302.984,
-      "eval_steps_per_second": 3.23,
+      "eval_runtime": 4.841,
+      "eval_samples_per_second": 310.059,
+      "eval_steps_per_second": 3.305,
       "step": 1
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 9.4375,
+      "grad_norm": 9.25,
       "learning_rate": 0.00019863613034027224,
-      "loss": 6.178,
+      "loss": 6.1788,
       "step": 10
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 5.375,
+      "grad_norm": 5.25,
       "learning_rate": 0.0001879473751206489,
-      "loss": 5.2701,
-      "step": 20
-    },
-    {
-      "epoch": 2.857142857142857,
-      "eval_loss": 3.3285892009735107,
-      "eval_runtime": 5.1935,
-      "eval_samples_per_second": 289.018,
-      "eval_steps_per_second": 3.081,
+      "loss": 5.2684,
       "step": 20
     },
     {
       "epoch": 4.285714285714286,
-      "grad_norm": 4.21875,
+      "grad_norm": 5.28125,
       "learning_rate": 0.00016772815716257412,
-      "loss": 4.6968,
+      "loss": 4.6887,
       "step": 30
     },
     {
       "epoch": 5.714285714285714,
-      "grad_norm": 2.421875,
+      "grad_norm": 2.3125,
       "learning_rate": 0.00014016954246529696,
-      "loss": 4.3713,
-      "step": 40
-    },
-    {
-      "epoch": 5.714285714285714,
-      "eval_loss": 3.2811784744262695,
-      "eval_runtime": 4.8,
-      "eval_samples_per_second": 312.707,
-      "eval_steps_per_second": 3.333,
+      "loss": 4.3802,
       "step": 40
     },
     {
       "epoch": 7.142857142857143,
-      "grad_norm": 2.578125,
+      "grad_norm": 3.484375,
       "learning_rate": 0.00010825793454723325,
-      "loss": 4.1039,
+      "loss": 4.1083,
       "step": 50
     },
     {
       "epoch": 8.571428571428571,
-      "grad_norm": 2.28125,
+      "grad_norm": 2.5625,
       "learning_rate": 7.54514512859201e-05,
-      "loss": 3.885,
-      "step": 60
-    },
-    {
-      "epoch": 8.571428571428571,
-      "eval_loss": 3.0508906841278076,
-      "eval_runtime": 4.9305,
-      "eval_samples_per_second": 304.43,
-      "eval_steps_per_second": 3.245,
+      "loss": 3.8961,
       "step": 60
     },
     {
       "epoch": 10.0,
-      "grad_norm": 2.828125,
+      "grad_norm": 2.96875,
       "learning_rate": 4.530518418775733e-05,
-      "loss": 3.7931,
+      "loss": 3.8097,
       "step": 70
     },
     {
       "epoch": 11.428571428571429,
-      "grad_norm": 1.5625,
+      "grad_norm": 1.546875,
       "learning_rate": 2.1085949060360654e-05,
-      "loss": 3.7326,
-      "step": 80
-    },
-    {
-      "epoch": 11.428571428571429,
-      "eval_loss": 3.0470147132873535,
-      "eval_runtime": 4.9222,
-      "eval_samples_per_second": 304.944,
-      "eval_steps_per_second": 3.251,
+      "loss": 3.7435,
       "step": 80
     },
     {
       "epoch": 12.857142857142858,
-      "grad_norm": 2.046875,
+      "grad_norm": 2.328125,
       "learning_rate": 5.418275829936537e-06,
-      "loss": 3.7097,
+      "loss": 3.721,
       "step": 90
     },
     {
       "epoch": 14.285714285714286,
-      "grad_norm": 1.6171875,
+      "grad_norm": 1.453125,
       "learning_rate": 0.0,
-      "loss": 3.6947,
-      "step": 100
-    },
-    {
-      "epoch": 14.285714285714286,
-      "eval_loss": 3.0370891094207764,
-      "eval_runtime": 5.0102,
-      "eval_samples_per_second": 299.59,
-      "eval_steps_per_second": 3.194,
+      "loss": 3.7058,
       "step": 100
     }
   ],
@@ -131,7 +91,7 @@
   "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 15,
-  "save_steps": 20,
+  "save_steps": 200,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c45a65d2feaa5c8b7363d20e9b9067a7c858a6c5c36582490c8414ec321027
+oid sha256:7bdfa99156b89b16ec5fa2a9dbf1b49622d09344a5aea17d9ad3478c38d45547
 size 6840