Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10acedbc50fa3d8c8d9dbe4eb7fab990e97c4fcef731b7ef8aad5b6f0f36fc31
+oid sha256:a4dfbf5d6e4b1919fd21b2c53d7a723a096c281b4d69231fc5d376272ecf657a
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca17de2a3f967c4fbbb47ab1fd051b2406152d9e83655a9085db81c67f9ce41e
+oid sha256:d6d3d7872d4b541c4fe16c783304a15ec781a39e428ef39089562b85553731ff
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c35ebbbf890f698cdf40bc9eba9c8ea419b358821e4143706913f24529731a
+oid sha256:a6b70c749d9fca7368a712c6e25aa110afedb1cf4d0c2fe8a0417ce2389e1f86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b353b67d3c68734cb4cbcb55694f7eeeb40f54128ba041a6736d420b09008b6
+oid sha256:ea4cdeda39ba2136e592d70ee5cca1961eef743b3307c81d32a1dfebf7fdaaa7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4069381058216095,
   "best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-5500",
-  "epoch": 239.1304347826087,
+  "epoch": 260.8695652173913,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -865,6 +865,84 @@
       "eval_samples_per_second": 11.867,
       "eval_steps_per_second": 1.548,
       "step": 5500
+    },
+    {
+      "epoch": 241.30434782608697,
+      "grad_norm": 0.866113007068634,
+      "learning_rate": 4.086666666666667e-06,
+      "loss": 0.4117,
+      "step": 5550
+    },
+    {
+      "epoch": 243.47826086956522,
+      "grad_norm": 0.8896365165710449,
+      "learning_rate": 4.003333333333334e-06,
+      "loss": 0.4161,
+      "step": 5600
+    },
+    {
+      "epoch": 245.65217391304347,
+      "grad_norm": 0.8311805129051208,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 0.4094,
+      "step": 5650
+    },
+    {
+      "epoch": 247.82608695652175,
+      "grad_norm": 1.686919927597046,
+      "learning_rate": 3.836666666666667e-06,
+      "loss": 0.4128,
+      "step": 5700
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 1.9034643173217773,
+      "learning_rate": 3.753333333333334e-06,
+      "loss": 0.4143,
+      "step": 5750
+    },
+    {
+      "epoch": 252.17391304347825,
+      "grad_norm": 0.8296219706535339,
+      "learning_rate": 3.6700000000000004e-06,
+      "loss": 0.4123,
+      "step": 5800
+    },
+    {
+      "epoch": 254.34782608695653,
+      "grad_norm": 0.6855341792106628,
+      "learning_rate": 3.5866666666666673e-06,
+      "loss": 0.4099,
+      "step": 5850
+    },
+    {
+      "epoch": 256.5217391304348,
+      "grad_norm": 1.0125635862350464,
+      "learning_rate": 3.5033333333333334e-06,
+      "loss": 0.4104,
+      "step": 5900
+    },
+    {
+      "epoch": 258.69565217391306,
+      "grad_norm": 0.8589877486228943,
+      "learning_rate": 3.4200000000000007e-06,
+      "loss": 0.4069,
+      "step": 5950
+    },
+    {
+      "epoch": 260.8695652173913,
+      "grad_norm": 0.9898667931556702,
+      "learning_rate": 3.3366666666666668e-06,
+      "loss": 0.4113,
+      "step": 6000
+    },
+    {
+      "epoch": 260.8695652173913,
+      "eval_loss": 0.40804117918014526,
+      "eval_runtime": 13.2074,
+      "eval_samples_per_second": 12.19,
+      "eval_steps_per_second": 1.59,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -884,7 +962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.665726342678198e+16,
+  "total_flos": 7.271570164893091e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null