Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6142c2c53af9538e6bca5c11779d85411a6ccfae246af05260fc0e789d0a884
+oid sha256:fc43df613783064dc44ad7bf103c22bfa8ef7b10427fc663355265232721757d
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4edbe6573268e48ee8396e594c97c268b69d2ff2af555df1afc65eaff422e469
-size 42608388
+oid sha256:6a7e28781e5fded2de29b4a971d82d09739c976296022fc6d885f3e936d285a7
+size 42608772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c5aa07c02af98d06cf7080ae86eca677d7649184ce0ff7e63a0c00ee5db2ed
+oid sha256:9fba15bd32b65c2624d5b20bddee991369e3780ef601a4b1645a7f5ee53b4661
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
+oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.154661774635315,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.19372336303758234,
+  "best_metric": 1.1374027729034424,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.2324680356450988,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 28.03,
       "eval_steps_per_second": 7.007,
       "step": 250
+    },
+    {
+      "epoch": 0.20147229755908563,
+      "grad_norm": 1.3052321672439575,
+      "learning_rate": 0.00011210963902166683,
+      "loss": 1.1019,
+      "step": 260
+    },
+    {
+      "epoch": 0.20922123208058893,
+      "grad_norm": 1.3270354270935059,
+      "learning_rate": 0.00010504229891530386,
+      "loss": 1.1695,
+      "step": 270
+    },
+    {
+      "epoch": 0.2169701666020922,
+      "grad_norm": 1.625852346420288,
+      "learning_rate": 9.795770108469618e-05,
+      "loss": 1.1769,
+      "step": 280
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 1.5025311708450317,
+      "learning_rate": 9.08903609783332e-05,
+      "loss": 1.1659,
+      "step": 290
+    },
+    {
+      "epoch": 0.2324680356450988,
+      "grad_norm": 3.024522066116333,
+      "learning_rate": 8.387470996680658e-05,
+      "loss": 1.1329,
+      "step": 300
+    },
+    {
+      "epoch": 0.2324680356450988,
+      "eval_loss": 1.1374027729034424,
+      "eval_runtime": 19.4072,
+      "eval_samples_per_second": 28.031,
+      "eval_steps_per_second": 7.008,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2993480405024768e+16,
+  "total_flos": 1.558212350312448e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null