Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289d391b5677975253230c6da38e1e938b7d7d2faf232ea7cf43f493e9f3c8ba
+oid sha256:391083bb43eb64b6662c39a468ec85e74df279702dc439348ef35201977a182c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e9a7bb719d28a6e186c37ca619d772a5524e3749da510a1820bf1ce57ebc0a
+oid sha256:40e02d2d068623134aa731d7c3c30f2767a1103e58700803565102ce8a55d714
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.364399790763855,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.010598834128245893,
+  "best_metric": 1.112984538078308,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.021197668256491786,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.979,
       "eval_steps_per_second": 2.489,
       "step": 10
+    },
+    {
+      "epoch": 0.011658717541070483,
+      "grad_norm": 1.573024868965149,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.4242,
+      "step": 11
+    },
+    {
+      "epoch": 0.012718600953895072,
+      "grad_norm": 1.2491636276245117,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.4373,
+      "step": 12
+    },
+    {
+      "epoch": 0.01377848436671966,
+      "grad_norm": 1.5084812641143799,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.8817,
+      "step": 13
+    },
+    {
+      "epoch": 0.01483836777954425,
+      "grad_norm": 2.022383451461792,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.9304,
+      "step": 14
+    },
+    {
+      "epoch": 0.01589825119236884,
+      "grad_norm": 1.9843780994415283,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.7349,
+      "step": 15
+    },
+    {
+      "epoch": 0.01589825119236884,
+      "eval_loss": 1.1954110860824585,
+      "eval_runtime": 79.8374,
+      "eval_samples_per_second": 4.985,
+      "eval_steps_per_second": 2.493,
+      "step": 15
+    },
+    {
+      "epoch": 0.01695813460519343,
+      "grad_norm": 1.3177485466003418,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.1256,
+      "step": 16
+    },
+    {
+      "epoch": 0.018018018018018018,
+      "grad_norm": 1.5878150463104248,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.7507,
+      "step": 17
+    },
+    {
+      "epoch": 0.019077901430842606,
+      "grad_norm": 1.2976889610290527,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.1571,
+      "step": 18
+    },
+    {
+      "epoch": 0.020137784843667197,
+      "grad_norm": 1.248026728630066,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.6085,
+      "step": 19
+    },
+    {
+      "epoch": 0.021197668256491786,
+      "grad_norm": 1.2782723903656006,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.5545,
+      "step": 20
+    },
+    {
+      "epoch": 0.021197668256491786,
+      "eval_loss": 1.112984538078308,
+      "eval_runtime": 83.6533,
+      "eval_samples_per_second": 4.758,
+      "eval_steps_per_second": 2.379,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257498484080640.0,
+  "total_flos": 6514996968161280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null