Training in progress, step 34, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba5b31852294f16cc452ebec610dc7cf066487a624e8e79249ccd302825369b4
+oid sha256:f04ef4511017ad729eb540c517cb5253fdf36214b26dab021a815c78cfdd9f21
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7119e690322d9466c4cbc43fc720418c360f05c866616c6c400c9608abcfdd2
+oid sha256:a00995990d35395ce0b7d69566d3bca91cffebf993ce813537038b4d4d630187
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ad921c40f84ae7d9721dae199ac1c6c825fdeef7abe0345a7fc313286c5808
+oid sha256:2faf73959cf1c9dc8d559795d29cae3bcdb9685f65df9cd6c6331b177e8e3f7b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:862c0f9dd6c537fb255622fb0273568e2fc6953235fbd5d195274a0ba501ac2c
+oid sha256:c92a7c5ff9f938337976875694bc290eaf4eb37ddf7da0ea8d60a1501a3f7a6c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9878a4872acdd2661b2d235b6f7410510e0364a40c6c5bc3a164a899274ea59
+oid sha256:ae22a01cbbc8f30bdbb7007aa3f5e6ce12bc39f75f30713d06e70ac8206cd655
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c220d2fbe9a2870f9ac93749b3d4b3852ce94b5983d948fa8de3d35e453f98ce
+oid sha256:7312f49c1e1b01f68cdaee175129535fda49cd22ed1f251a2745d2c8c42996be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.209366391184573,
+  "epoch": 3.005509641873278,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 9.931,
       "eval_steps_per_second": 2.582,
       "step": 25
+    },
+    {
+      "epoch": 2.2975206611570247,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.3856749311294765,
+      "grad_norm": NaN,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.4738292011019283,
+      "grad_norm": NaN,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.56198347107438,
+      "grad_norm": NaN,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.650137741046832,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.7382920110192837,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.8264462809917354,
+      "grad_norm": NaN,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.9146005509641872,
+      "grad_norm": NaN,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 3.005509641873278,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7794733001814835e+17,
+  "total_flos": 3.780846331845673e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null