Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4640cdfd5049fa55f638b28d54cd06e5001e7d6ec0e00957bc1d8edde2a495a
+oid sha256:1010df5598a57f3107191c355d0821d0298565ed53102d05d42a80266f4acd01
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a56a8a2bc15f4d758b0eb9991e9912dcd8f3557ca8a359e579b699adf35587
+oid sha256:66d9db11aeb77fe2fa3bbb095fdaa33941577676015deecc0a95e5769fbe593a
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7bb138aa5106db6be0a3fa0ca8b584ca968cb624961c21434f43b0f94a7f53
+oid sha256:61466e9412c0d194297480cf7f0e3a714d962a2892349d2aadf71260158ae2fe
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d5b14b9a348d0c0d9daa4cabaaf2992e8a1a55a0f722d47cf938ca82885ab9
+oid sha256:a7eb88890e8a1c0d8205803f09e7feb7113f18f444391d019b68607e3c736e37
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dff6d0a97e77162b13dd1d33a894b8edaf14cd2511685238f1583301c4a8320
+oid sha256:cb18b777ebcd388d89ae9a04b334b4e4327bc4436d4f89f04f67b009aa0dea99
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5333333333333333,
+  "epoch": 0.6666666666666666,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -640,6 +640,164 @@
       "eval_samples_per_second": 7.616,
       "eval_steps_per_second": 0.381,
       "step": 8000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.9676337838172913,
+      "learning_rate": 0.0001901272875992957,
+      "loss": 8.395182495117188,
+      "step": 8100
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 1.0351442098617554,
+      "learning_rate": 0.0001857261660685435,
+      "loss": 8.413995361328125,
+      "step": 8200
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 0.987281322479248,
+      "learning_rate": 0.00018133198187916734,
+      "loss": 8.399580688476563,
+      "step": 8300
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.9454151391983032,
+      "learning_rate": 0.00017694687068413458,
+      "loss": 8.42725341796875,
+      "step": 8400
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 1.0215506553649902,
+      "learning_rate": 0.00017257296372677328,
+      "loss": 8.389710693359374,
+      "step": 8500
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.0646560192108154,
+      "learning_rate": 0.00016821238680494918,
+      "loss": 8.27107177734375,
+      "step": 8600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.016783356666565,
+      "learning_rate": 0.00016386725923789007,
+      "loss": 8.3458056640625,
+      "step": 8700
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.029847502708435,
+      "learning_rate": 0.00015953969283615782,
+      "loss": 8.26437744140625,
+      "step": 8800
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.982424259185791,
+      "learning_rate": 0.0001552317908752705,
+      "loss": 8.396544189453126,
+      "step": 8900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.958069384098053,
+      "learning_rate": 0.0001509456470734723,
+      "loss": 8.241473388671874,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.3059334637964775,
+      "eval_loss": 8.307632446289062,
+      "eval_runtime": 65.4278,
+      "eval_samples_per_second": 7.642,
+      "eval_steps_per_second": 0.382,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 1.1917734146118164,
+      "learning_rate": 0.0001466833445741486,
+      "loss": 8.325388793945313,
+      "step": 9100
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.0918893814086914,
+      "learning_rate": 0.0001424469549333809,
+      "loss": 8.24582763671875,
+      "step": 9200
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9687617421150208,
+      "learning_rate": 0.0001382385371131328,
+      "loss": 8.22963134765625,
+      "step": 9300
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 1.2594196796417236,
+      "learning_rate": 0.0001340601364805574,
+      "loss": 8.203480224609375,
+      "step": 9400
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 1.327571153640747,
+      "learning_rate": 0.00012991378381391192,
+      "loss": 8.20176513671875,
+      "step": 9500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0071412324905396,
+      "learning_rate": 0.0001258014943155624,
+      "loss": 8.172748413085937,
+      "step": 9600
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 1.0164071321487427,
+      "learning_rate": 0.00012172526663255951,
+      "loss": 8.214456787109375,
+      "step": 9700
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 1.1246143579483032,
+      "learning_rate": 0.00011768708188525956,
+      "loss": 8.266552734375,
+      "step": 9800
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0247814655303955,
+      "learning_rate": 0.00011368890270446406,
+      "loss": 8.150130004882813,
+      "step": 9900
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.0046054124832153,
+      "learning_rate": 0.00010973267227754613,
+      "loss": 8.194937744140624,
+      "step": 10000
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_accuracy": 0.30975342465753425,
+      "eval_loss": 8.204855918884277,
+      "eval_runtime": 65.6714,
+      "eval_samples_per_second": 7.614,
+      "eval_steps_per_second": 0.381,
+      "step": 10000
     }
   ],
   "logging_steps": 100,