Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e880a536163c2986381e3a12a056bbf8f83f6eaf18d0eb40148f42c680c8860
+oid sha256:f99240f5ab1709ed93bfa9e6f1ee1bcd5a3d8521cca85e6d37ebb3443ee2aa77
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383824750403cf003a7d75a422035ecb2781727e3d676003b07865afd628199f
+oid sha256:29e7d19c9d6cc922ce505795ccd9e5e56deadc0e4e45536de43d9b2884513617
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cd91016c05522d65bf761ff7d6665aaf444fe68fe7396c3f093e41e4303b9a
+oid sha256:9f26228cdef39b900b7538fa5e6fd502177411408e4d296d7daf626ba036a98b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3195807933807373,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5025125628140703,
+  "best_metric": 2.249424457550049,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0050251256281406,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 26.288,
       "eval_steps_per_second": 3.442,
       "step": 25
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 4.022976875305176,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.2623,
+      "step": 26
+    },
+    {
+      "epoch": 0.542713567839196,
+      "grad_norm": 2.966477870941162,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.2134,
+      "step": 27
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 3.3126888275146484,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2434,
+      "step": 28
+    },
+    {
+      "epoch": 0.5829145728643216,
+      "grad_norm": 2.846015214920044,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.2769,
+      "step": 29
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 2.731851816177368,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.181,
+      "step": 30
+    },
+    {
+      "epoch": 0.6231155778894473,
+      "grad_norm": 2.8917224407196045,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.1915,
+      "step": 31
+    },
+    {
+      "epoch": 0.6432160804020101,
+      "grad_norm": 2.9384567737579346,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1434,
+      "step": 32
+    },
+    {
+      "epoch": 0.6633165829145728,
+      "grad_norm": 3.4760513305664062,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.1318,
+      "step": 33
+    },
+    {
+      "epoch": 0.6834170854271356,
+      "grad_norm": 3.2303836345672607,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9966,
+      "step": 34
+    },
+    {
+      "epoch": 0.7035175879396985,
+      "grad_norm": 3.0314648151397705,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0142,
+      "step": 35
+    },
+    {
+      "epoch": 0.7236180904522613,
+      "grad_norm": 3.890491247177124,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2815,
+      "step": 36
+    },
+    {
+      "epoch": 0.7437185929648241,
+      "grad_norm": 3.0645134449005127,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.1619,
+      "step": 37
+    },
+    {
+      "epoch": 0.7638190954773869,
+      "grad_norm": 3.3046720027923584,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.286,
+      "step": 38
+    },
+    {
+      "epoch": 0.7839195979899497,
+      "grad_norm": 3.647308111190796,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.3693,
+      "step": 39
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 3.0381925106048584,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.1782,
+      "step": 40
+    },
+    {
+      "epoch": 0.8241206030150754,
+      "grad_norm": 2.8741769790649414,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1408,
+      "step": 41
+    },
+    {
+      "epoch": 0.8442211055276382,
+      "grad_norm": 3.271303653717041,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0242,
+      "step": 42
+    },
+    {
+      "epoch": 0.864321608040201,
+      "grad_norm": 2.9552042484283447,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.3821,
+      "step": 43
+    },
+    {
+      "epoch": 0.8844221105527639,
+      "grad_norm": 2.8075811862945557,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9033,
+      "step": 44
+    },
+    {
+      "epoch": 0.9045226130653267,
+      "grad_norm": 2.864377975463867,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8498,
+      "step": 45
+    },
+    {
+      "epoch": 0.9246231155778895,
+      "grad_norm": 2.87247896194458,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.9853,
+      "step": 46
+    },
+    {
+      "epoch": 0.9447236180904522,
+      "grad_norm": 3.5218048095703125,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0811,
+      "step": 47
+    },
+    {
+      "epoch": 0.964824120603015,
+      "grad_norm": 4.313379764556885,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.3161,
+      "step": 48
+    },
+    {
+      "epoch": 0.9849246231155779,
+      "grad_norm": 3.7471933364868164,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.2004,
+      "step": 49
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 4.189254283905029,
+      "learning_rate": 0.0,
+      "loss": 3.0137,
+      "step": 50
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "eval_loss": 2.249424457550049,
+      "eval_runtime": 3.2079,
+      "eval_samples_per_second": 26.185,
+      "eval_steps_per_second": 3.429,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.88564197343232e+16,
+  "total_flos": 3.759498684530688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null