Training in progress, step 904, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b0e3c3bd26131ebebc0107592dfb0e3ffac7006161cec8157da1447bcf1f26
+oid sha256:38620c4bf2bc9c7937f6a727f2abec8b72e8fb55317062ec219d8e2ef7accc87
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f70e7042d2a0de78962d26038567750368b9ea96f85798f609af6eb09cebbc
+oid sha256:3f76e3915886a8830e40637e927907671327b3f91d30dcbe399af86f7e695565
 size 1279647314

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79f7225a96d99f97c5e021e9970c5a6e310a7ca5f96ef7ad1b3a4b0ca1a07a7
+oid sha256:38e826a1a20e9f6f0fa80e2b7b21b704647fdaf10667e527df01d00dcf45477d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27cbe3194fd7f6cc56537348ff9006bc0d05939c0e80cef4d6e67c9e0002f35c
+oid sha256:382422162aab33948581084e52d0ed87967c2d8174632ac480d9dcce673b65af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.18988579511642456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-452",
-  "epoch": 0.4075284571170968,
+  "best_metric": 0.14215713739395142,
+  "best_model_checkpoint": "miner_id_24/checkpoint-904",
+  "epoch": 0.8150569142341936,
   "eval_steps": 452,
-  "global_step": 452,
+  "global_step": 904,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,6 +86,77 @@
       "eval_samples_per_second": 10.101,
       "eval_steps_per_second": 2.525,
       "step": 452
+    },
+    {
+      "epoch": 0.45080581539501857,
+      "grad_norm": 0.43745195865631104,
+      "learning_rate": 0.00010934790878943365,
+      "loss": 0.184,
+      "step": 500
+    },
+    {
+      "epoch": 0.49588639693452047,
+      "grad_norm": 0.5013279318809509,
+      "learning_rate": 8.826908410935261e-05,
+      "loss": 0.1736,
+      "step": 550
+    },
+    {
+      "epoch": 0.5409669784740223,
+      "grad_norm": 0.3170182406902313,
+      "learning_rate": 6.796003003915074e-05,
+      "loss": 0.1644,
+      "step": 600
+    },
+    {
+      "epoch": 0.5860475600135242,
+      "grad_norm": 0.27928972244262695,
+      "learning_rate": 4.9193490285647315e-05,
+      "loss": 0.1575,
+      "step": 650
+    },
+    {
+      "epoch": 0.631128141553026,
+      "grad_norm": 0.30695998668670654,
+      "learning_rate": 3.268351708599568e-05,
+      "loss": 0.1591,
+      "step": 700
+    },
+    {
+      "epoch": 0.6762087230925279,
+      "grad_norm": 0.3712688088417053,
+      "learning_rate": 1.9058302075595738e-05,
+      "loss": 0.1562,
+      "step": 750
+    },
+    {
+      "epoch": 0.7212893046320298,
+      "grad_norm": 0.34539204835891724,
+      "learning_rate": 8.836274085103583e-06,
+      "loss": 0.1454,
+      "step": 800
+    },
+    {
+      "epoch": 0.7663698861715316,
+      "grad_norm": 0.46884703636169434,
+      "learning_rate": 2.4063733267654535e-06,
+      "loss": 0.1446,
+      "step": 850
+    },
+    {
+      "epoch": 0.8114504677110335,
+      "grad_norm": 0.3394332230091095,
+      "learning_rate": 1.3252521939148497e-08,
+      "loss": 0.1523,
+      "step": 900
+    },
+    {
+      "epoch": 0.8150569142341936,
+      "eval_loss": 0.14215713739395142,
+      "eval_runtime": 185.7159,
+      "eval_samples_per_second": 10.058,
+      "eval_steps_per_second": 2.515,
+      "step": 904
     }
   ],
   "logging_steps": 50,
@@ -109,12 +180,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.013840899660841e+17,
+  "total_flos": 1.2027681799321682e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null