Training in progress, step 49, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d430853bfd2a3418faad367efb6a483db40cc4fcbf81319985dbc5fd86549dd4
+oid sha256:d85a7d3fe530ae7eea809a442097025a30ad759735b6bb55a5d097aff6d50780
 size 240145026

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8db04a03c6a2c077cf77fe4c8771a388d21bb116c83f663580ba87efc599103
+oid sha256:8687dc146666ead4a5cf594dc0428203e9da72126d9a8dbe873d7d72a8cd34dc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846f2a444a76ee86bd221efb718aa24fea43ff502c7ad9b632975399c4a31177
+oid sha256:bb80d6ff56197631b4bdbf469290dfc433f148d9b5bdb1b53bad217635c1c057
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c928b0884d94106fcd241859508d607d85931ff0cb10d9101483ee13152a70
+oid sha256:c16c60142345b41bff4a442b6916ff7d12e87cd4ac3850da3bab877c2297a455
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa999e19ce796149009f665f3e194a38530002e3136d5ab1bebe1fadf107530
+oid sha256:0c2f478f228dd67843721480a5bce10f42bd58f501cc8631a64b248e211f1dc1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8339621e0254150598b8a53ec927095b94a662289d4252af9f13d6ac65a483e
+oid sha256:c3beede4336a46640c9aa1536e08db38f31dc18c73764913b78bf6e9f1d29144
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.5384615384615383,
+  "epoch": 3.0153846153846153,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,174 @@
       "eval_samples_per_second": 81.718,
       "eval_steps_per_second": 21.247,
       "step": 25
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": NaN,
+      "learning_rate": 5.349632603465466e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "grad_norm": NaN,
+      "learning_rate": 5.049569387691557e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "grad_norm": NaN,
+      "learning_rate": 4.751517904375915e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": NaN,
+      "learning_rate": 4.456809323796123e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": NaN,
+      "learning_rate": 4.166759886014648e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "grad_norm": NaN,
+      "learning_rate": 3.882665022231193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": NaN,
+      "learning_rate": 3.605793569072493e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "grad_norm": NaN,
+      "learning_rate": 3.337382101659923e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": NaN,
+      "learning_rate": 3.078629410764824e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": NaN,
+      "learning_rate": 2.830691148717902e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "grad_norm": NaN,
+      "learning_rate": 2.5946746679853894e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": NaN,
+      "learning_rate": 2.3716340754641102e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "grad_norm": NaN,
+      "learning_rate": 2.162565524584191e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": NaN,
+      "learning_rate": 1.9684027662460257e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": NaN,
+      "learning_rate": 1.79001297846208e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.523076923076923,
+      "grad_norm": NaN,
+      "learning_rate": 1.628192893329374e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "grad_norm": NaN,
+      "learning_rate": 1.4836652386305349e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": NaN,
+      "learning_rate": 1.35707550995607e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.707692307692308,
+      "grad_norm": NaN,
+      "learning_rate": 1.248989087764366e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": NaN,
+      "learning_rate": 1.1598887122553061e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": NaN,
+      "learning_rate": 1.0901723273353597e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "grad_norm": NaN,
+      "learning_rate": 1.04015130330349e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": NaN,
+      "learning_rate": 1.0100490461958109e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 3.0153846153846153,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 49
     }
   ],
   "logging_steps": 1,
@@ -221,12 +389,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.1506187337728e+16,
+  "total_flos": 1.0095212718194688e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null