Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9316c838a4ba6bc9d3418a91e68d71abe7862a1e437d69ff40c8fe881ba39092
+oid sha256:5434b9cf4d5558e342af70598c8c6733f13acd1f97262fb13db6746964ce9835
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306457dc3697a50ccc6bb598a082c5aa904f0655f1405c4226710f97d2dd633c
+oid sha256:51a4b6d90bbeff02a96411808916502d60438b05e8dbd2c995afeea20756e58f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 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": 0.46889933943748474,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.022922636103151862,
+  "best_metric": 0.3845430910587311,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.045845272206303724,
   "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": 3.34,
       "eval_steps_per_second": 1.67,
       "step": 10
+    },
+    {
+      "epoch": 0.02521489971346705,
+      "grad_norm": 4.640089511871338,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.0298,
+      "step": 11
+    },
+    {
+      "epoch": 0.027507163323782235,
+      "grad_norm": 6.224593639373779,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.1778,
+      "step": 12
+    },
+    {
+      "epoch": 0.02979942693409742,
+      "grad_norm": 4.25213098526001,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.7744,
+      "step": 13
+    },
+    {
+      "epoch": 0.032091690544412604,
+      "grad_norm": 4.979966640472412,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.6806,
+      "step": 14
+    },
+    {
+      "epoch": 0.034383954154727794,
+      "grad_norm": 4.518800258636475,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6474,
+      "step": 15
+    },
+    {
+      "epoch": 0.034383954154727794,
+      "eval_loss": 0.40958088636398315,
+      "eval_runtime": 54.7398,
+      "eval_samples_per_second": 3.361,
+      "eval_steps_per_second": 1.681,
+      "step": 15
+    },
+    {
+      "epoch": 0.03667621776504298,
+      "grad_norm": 4.9027323722839355,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7134,
+      "step": 16
+    },
+    {
+      "epoch": 0.03896848137535817,
+      "grad_norm": 4.276649475097656,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.7094,
+      "step": 17
+    },
+    {
+      "epoch": 0.04126074498567335,
+      "grad_norm": 4.055666923522949,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5544,
+      "step": 18
+    },
+    {
+      "epoch": 0.04355300859598854,
+      "grad_norm": 4.310039043426514,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.6613,
+      "step": 19
+    },
+    {
+      "epoch": 0.045845272206303724,
+      "grad_norm": 3.8238983154296875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5674,
+      "step": 20
+    },
+    {
+      "epoch": 0.045845272206303724,
+      "eval_loss": 0.3845430910587311,
+      "eval_runtime": 54.5459,
+      "eval_samples_per_second": 3.373,
+      "eval_steps_per_second": 1.687,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3505343598428160.0,
+  "total_flos": 7010687196856320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null