Training in progress, step 154, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b0d11a0c9563fc9b309894a3ea72052d18d47c5d2c7383d7f135a6f7e75bbf6
+oid sha256:16eef88422eb94e9d2420c95c1375df312b1b4ea595f24762f20b983747efe41
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc19d3760e42bf952fe3f4416369525889e94276e27e85715f534215e6d1fbc
+oid sha256:764882108bdabde9c120b53d694588407379bf3cd5cf8bd51f06ae98b1b6ad60
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ad0144eca33b04b3d4f2b29d4af62fc22d673739ee2272250b1b21f6f349c2
+oid sha256:e4b80374eb5b525a1eeb346cf4a22f7c07b53619389a7567c8fe8c3ad7a7556e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f01b3d4386ea634ed6767aa1edfa6779ba81e1725f3e3e0c0b9a9f92776b83
+oid sha256:8571cd03298231074ef5da5a91b5f7c590ccf8c044bb8f89ab9ac55f0cf228ef
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5bb99b77e13ee757e01e8e860bc41eebc1421459e9c89d0a23b81def884f78
+oid sha256:544e1be73a65477247874aeff645c2a77a03a2386f9c039f21691e67953dda30
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e625baf0c17e4ad56e8b11a83cbda177c07e59a3d18f926b7eb718549b22f65
+oid sha256:4625c8f0544987395688ac4e887e1102183e1a5a7bbc24905bde6ed4147e8ae4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a56f9e526fbefceff44eaa8fd41d4c73340d4c2a80ffbd5f860cb7089f42cc1
+oid sha256:0500dcde4e9286f0efc9accf05125c4dfcf1e260a707c8323234408753d49e72
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9268525838851929,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 1.955193482688391,
+  "epoch": 2.0073319755600814,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 154,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1113,6 +1113,34 @@
       "eval_samples_per_second": 176.994,
       "eval_steps_per_second": 46.019,
       "step": 150
+    },
+    {
+      "epoch": 1.9682281059063138,
+      "grad_norm": 0.5727090835571289,
+      "learning_rate": 3.0266391662183335e-05,
+      "loss": 2.0008,
+      "step": 151
+    },
+    {
+      "epoch": 1.9812627291242362,
+      "grad_norm": 0.6628953814506531,
+      "learning_rate": 3.0118417936654115e-05,
+      "loss": 2.2794,
+      "step": 152
+    },
+    {
+      "epoch": 1.994297352342159,
+      "grad_norm": 0.3259391188621521,
+      "learning_rate": 3.0029607730895854e-05,
+      "loss": 2.0307,
+      "step": 153
+    },
+    {
+      "epoch": 2.0073319755600814,
+      "grad_norm": 0.36595845222473145,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.3735,
+      "step": 154
     }
   ],
   "logging_steps": 1,
@@ -1136,12 +1164,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.66420413202432e+16,
+  "total_flos": 6.841916242211635e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null