Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035117b09dfdc6d12c531cfa1a299a6930aa3a0980fda5f4ee497e90ef6b21a2
+oid sha256:ec22c3d9bcd6353319973a9b948e015bf2b55e5b016dd4a047ac623b8d75a936
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a7fd3a5cb53128eff1159920c614d981a3c68664d5045b0c30873828f04da0
+oid sha256:bc8ad9821b5b1d9d37cd3a4a43587f5f9ffc47c277706630426b4c035c536e57
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99eeec94447248854bf811d769a2a208fc950d0961184a4f99f03ffdc252b32b
+oid sha256:2a010ad19aaaa343fbfbf6d1ce05dfd1e56fb0ac07188b993fc06e025d81ccc1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1a187666ea0e44f9d015f844e1601f5b4c6844588e1b362a3c9b6a7527a74f
+oid sha256:8210f8e2249c280ac4965b4cc059199e79e619c33beb58bb250012029c0aaadf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4793977439403534,
-  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-500",
-  "epoch": 0.837696335078534,
+  "best_metric": 0.402164101600647,
+  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-1000",
+  "epoch": 1.675392670157068,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,84 @@
       "eval_samples_per_second": 32.024,
       "eval_steps_per_second": 4.006,
       "step": 500
+    },
+    {
+      "epoch": 0.9214659685863874,
+      "grad_norm": 2.2309463024139404,
+      "learning_rate": 2.7450000000000003e-05,
+      "loss": 0.5084,
+      "step": 550
+    },
+    {
+      "epoch": 1.0052356020942408,
+      "grad_norm": 1.8079086542129517,
+      "learning_rate": 2.995e-05,
+      "loss": 0.4954,
+      "step": 600
+    },
+    {
+      "epoch": 1.0890052356020943,
+      "grad_norm": 6.239879608154297,
+      "learning_rate": 3.245e-05,
+      "loss": 0.4954,
+      "step": 650
+    },
+    {
+      "epoch": 1.1727748691099475,
+      "grad_norm": 12.593622207641602,
+      "learning_rate": 3.495e-05,
+      "loss": 0.4946,
+      "step": 700
+    },
+    {
+      "epoch": 1.256544502617801,
+      "grad_norm": 3.1568186283111572,
+      "learning_rate": 3.745e-05,
+      "loss": 0.4768,
+      "step": 750
+    },
+    {
+      "epoch": 1.3403141361256545,
+      "grad_norm": 3.9486255645751953,
+      "learning_rate": 3.995e-05,
+      "loss": 0.4737,
+      "step": 800
+    },
+    {
+      "epoch": 1.4240837696335078,
+      "grad_norm": 2.641502618789673,
+      "learning_rate": 4.245e-05,
+      "loss": 0.4706,
+      "step": 850
+    },
+    {
+      "epoch": 1.5078534031413613,
+      "grad_norm": 1.9798855781555176,
+      "learning_rate": 4.495e-05,
+      "loss": 0.4605,
+      "step": 900
+    },
+    {
+      "epoch": 1.5916230366492146,
+      "grad_norm": 2.691363573074341,
+      "learning_rate": 4.745e-05,
+      "loss": 0.4554,
+      "step": 950
+    },
+    {
+      "epoch": 1.675392670157068,
+      "grad_norm": 3.704902410507202,
+      "learning_rate": 4.995e-05,
+      "loss": 0.4561,
+      "step": 1000
+    },
+    {
+      "epoch": 1.675392670157068,
+      "eval_loss": 0.402164101600647,
+      "eval_runtime": 265.618,
+      "eval_samples_per_second": 31.959,
+      "eval_steps_per_second": 3.998,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -104,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8963407491426432.0,
+  "total_flos": 1.791435708710208e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null