Training in progress, step 20, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd5b3fe28539d7c27e9c1c72289ef993f1955987b0acb6a12cc40eca8ba1e3a
+oid sha256:a32226883a7ac50cf6cdbc8be3102d173e1907b7a8ed2376557a3d33d01b2367
 size 4943162336

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406d436e48e98f1c89ab6ba1e12b026d54e9080c4538d743c32e9130af202cda
+oid sha256:c09202edeafe5745b96094f13f01f5c2116e51dae7201eff329f3fbb73d0b219
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b75146ff6313b5530681487be10972d2689efa7f86e01835f0e8e234259e58
+oid sha256:f80cb8df7b71b0e9b29b59e5f6dc8c04ccc38c0d087aaaba76e08b2a6df8cb58
 size 4540516344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7740f15c24140e82b6c0b040019d660922f8640fdac7298adf2e4d4e2cc315d
+oid sha256:d8144c06cc4e463d75d11b2c6eee14c47522fe31b4d94c4b73d58f0e4ca64e80
 size 14710121812

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f20d155a14d34cd1bb6d04e5de90f3224906e1758821edd752a8f1a9085a2db
+oid sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad18e870a176ca75a54f6620f83de92bdfd5a91302744d90bff8e5feae2fe0c5
+oid sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9009a52be47b75834407dc5e146ed5360e6f23a35bff27bab34ef6fb47df1661
+oid sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb494a08fd57e7c6f63f06826c872164986e81b271996be0496671f713bdcc3
+oid sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
+oid sha256:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9047619047619047,
-  "eval_steps": 200,
-  "global_step": 200,
+  "epoch": 0.19047619047619047,
+  "eval_steps": 20,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,165 +11,39 @@
     {
       "epoch": 0.009523809523809525,
       "eval_loss": 2.9466392993927,
-      "eval_runtime": 27.5938,
-      "eval_samples_per_second": 54.396,
-      "eval_steps_per_second": 6.813,
+      "eval_runtime": 27.7048,
+      "eval_samples_per_second": 54.178,
+      "eval_steps_per_second": 6.786,
       "step": 1
     },
     {
       "epoch": 0.09523809523809523,
-      "grad_norm": 12.75,
+      "grad_norm": 14.3125,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 1.837,
+      "loss": 1.8374,
       "step": 10
     },
     {
       "epoch": 0.19047619047619047,
-      "grad_norm": 374.0,
+      "grad_norm": 174.0,
       "learning_rate": 0.00013333333333333334,
-      "loss": 3.3823,
+      "loss": 2.7612,
       "step": 20
     },
     {
-      "epoch": 0.2857142857142857,
-      "grad_norm": 278.0,
-      "learning_rate": 0.0002,
-      "loss": 8.7342,
-      "step": 30
-    },
-    {
-      "epoch": 0.38095238095238093,
-      "grad_norm": 20.375,
-      "learning_rate": 0.00019984815164333163,
-      "loss": 7.9113,
-      "step": 40
-    },
-    {
-      "epoch": 0.47619047619047616,
-      "grad_norm": 16.375,
-      "learning_rate": 0.00019939306773179497,
-      "loss": 7.5732,
-      "step": 50
-    },
-    {
-      "epoch": 0.5714285714285714,
-      "grad_norm": 22.75,
-      "learning_rate": 0.00019863613034027224,
-      "loss": 7.4921,
-      "step": 60
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 20.625,
-      "learning_rate": 0.00019757963826274357,
-      "loss": 7.4366,
-      "step": 70
-    },
-    {
-      "epoch": 0.7619047619047619,
-      "grad_norm": 16.125,
-      "learning_rate": 0.00019622680003092503,
-      "loss": 7.4257,
-      "step": 80
-    },
-    {
-      "epoch": 0.8571428571428571,
-      "grad_norm": 7.40625,
-      "learning_rate": 0.00019458172417006347,
-      "loss": 7.4216,
-      "step": 90
-    },
-    {
-      "epoch": 0.9523809523809523,
-      "grad_norm": 8.375,
-      "learning_rate": 0.00019264940672148018,
-      "loss": 7.3601,
-      "step": 100
-    },
-    {
-      "epoch": 1.0476190476190477,
-      "grad_norm": 23.5,
-      "learning_rate": 0.00019043571606975777,
-      "loss": 7.3852,
-      "step": 110
-    },
-    {
-      "epoch": 1.1428571428571428,
-      "grad_norm": 13.3125,
-      "learning_rate": 0.0001879473751206489,
-      "loss": 7.3812,
-      "step": 120
-    },
-    {
-      "epoch": 1.2380952380952381,
-      "grad_norm": 6.59375,
-      "learning_rate": 0.00018519194088383273,
-      "loss": 7.3577,
-      "step": 130
-    },
-    {
-      "epoch": 1.3333333333333333,
-      "grad_norm": 7.8125,
-      "learning_rate": 0.0001821777815225245,
-      "loss": 7.3803,
-      "step": 140
-    },
-    {
-      "epoch": 1.4285714285714286,
-      "grad_norm": 12.75,
-      "learning_rate": 0.00017891405093963938,
-      "loss": 7.3922,
-      "step": 150
-    },
-    {
-      "epoch": 1.5238095238095237,
-      "grad_norm": 7.90625,
-      "learning_rate": 0.00017541066097768963,
-      "loss": 7.3621,
-      "step": 160
-    },
-    {
-      "epoch": 1.619047619047619,
-      "grad_norm": 29.0,
-      "learning_rate": 0.00017167825131684513,
-      "loss": 7.3791,
-      "step": 170
-    },
-    {
-      "epoch": 1.7142857142857144,
-      "grad_norm": 9.6875,
-      "learning_rate": 0.00016772815716257412,
-      "loss": 7.2719,
-      "step": 180
-    },
-    {
-      "epoch": 1.8095238095238095,
-      "grad_norm": 22.875,
-      "learning_rate": 0.00016357237482099684,
-      "loss": 7.2466,
-      "step": 190
-    },
-    {
-      "epoch": 1.9047619047619047,
-      "grad_norm": 22.0,
-      "learning_rate": 0.00015922352526649803,
-      "loss": 7.2034,
-      "step": 200
-    },
-    {
-      "epoch": 1.9047619047619047,
-      "eval_loss": 7.211991310119629,
-      "eval_runtime": 26.3918,
-      "eval_samples_per_second": 56.874,
-      "eval_steps_per_second": 7.123,
-      "step": 200
+      "epoch": 0.19047619047619047,
+      "eval_loss": 4.765164852142334,
+      "eval_runtime": 26.926,
+      "eval_samples_per_second": 55.745,
+      "eval_steps_per_second": 6.982,
+      "step": 20
     }
   ],
   "logging_steps": 10,
   "max_steps": 600,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 6,
-  "save_steps": 200,
+  "save_steps": 20,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -182,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3980127138414592e+17,
+  "total_flos": 1.3980127138414592e+16,
   "train_batch_size": 2,
   "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:adab2cd4b892729a3f8cb9343d382b49be7d93397bee49b30af6cf5be7d19904
+oid sha256:4a5d19d346ef788eb8cb46e90b86369e226e8da241f52a6ee5f2d5fb6f0845b8
 size 7736