Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8183302adcdb7f075cb84d5c8100d7b3c839d9c4e71c1fc2587d791ce1b07766
+oid sha256:ef5950b3e173f515ffb1ebfe5344182b14cef393439715212c1455c04d3f7ebd
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa13d76645227915df00aa8805fa4f84c955e764e5b3224c117c7690f4f21f7
+oid sha256:63b1ccc2423e6bd26680c5d9f3effda6f2cb4f4a2f5d937ac8d5dc4b585e1d1e
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beda58126156f4f955e4a64cbd24c28b181f86d8275703ca7a2c9db39ac2a373
+oid sha256:ec222382215b1fd911e1f9d923ef83dc7c6f7ea48c4d37361f397d827c182756
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.398805618286133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.009029345372460496,
+  "best_metric": 3.7718515396118164,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.01805869074492099,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 2.171,
       "eval_steps_per_second": 1.088,
       "step": 10
+    },
+    {
+      "epoch": 0.010835214446952596,
+      "grad_norm": 0.947878897190094,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 4.128,
+      "step": 12
+    },
+    {
+      "epoch": 0.013544018058690745,
+      "grad_norm": 1.2918604612350464,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.2702,
+      "step": 15
+    },
+    {
+      "epoch": 0.013544018058690745,
+      "eval_loss": 4.007048606872559,
+      "eval_runtime": 215.49,
+      "eval_samples_per_second": 2.167,
+      "eval_steps_per_second": 1.086,
+      "step": 15
+    },
+    {
+      "epoch": 0.016252821670428894,
+      "grad_norm": 1.323457956314087,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.1544,
+      "step": 18
+    },
+    {
+      "epoch": 0.01805869074492099,
+      "eval_loss": 3.7718515396118164,
+      "eval_runtime": 214.2875,
+      "eval_samples_per_second": 2.179,
+      "eval_steps_per_second": 1.092,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7165146606600192.0,
+  "total_flos": 1.4155533539868672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null