Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29823f4e08b18743fec2278d0a24fba91846a1bbe1838f5c71ac01c15fea6da1
+oid sha256:0c455923ab770e48cc7fe8b3335bf5b07469208adc770e09d20b199364122c4e
 size 1163996488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2febce13ec52a548e34b9db0f50c7fb2dfb945379b97f53fb52a73c2635c2f2c
+oid sha256:69011464ee6bf6a2e340fa6f5ccb7dac9287a6b7576359b1b0f5fadc01fa0606
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4787c2c04c07c1ae6e2c20c42952d1e91343f26f99f548d3534a1670bc4a5f0c
+oid sha256:cecbe0d896bc69bdfaae08801620d68150df363e8dc6b04330ef464a0d971be6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.613823652267456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.338409475465313,
+  "best_metric": 1.5217487812042236,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.4512126339537507,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -389,6 +389,126 @@
       "eval_samples_per_second": 13.426,
       "eval_steps_per_second": 3.361,
       "step": 150
+    },
+    {
+      "epoch": 0.34517766497461927,
+      "grad_norm": 1.9749424457550049,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 2.1616,
+      "step": 153
+    },
+    {
+      "epoch": 0.35194585448392557,
+      "grad_norm": 2.1206893920898438,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 2.1542,
+      "step": 156
+    },
+    {
+      "epoch": 0.3587140439932318,
+      "grad_norm": 2.122969150543213,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 1.9048,
+      "step": 159
+    },
+    {
+      "epoch": 0.36548223350253806,
+      "grad_norm": 2.1160035133361816,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8025,
+      "step": 162
+    },
+    {
+      "epoch": 0.37225042301184436,
+      "grad_norm": 2.0058743953704834,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 1.7525,
+      "step": 165
+    },
+    {
+      "epoch": 0.3790186125211506,
+      "grad_norm": 1.7620965242385864,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 1.4851,
+      "step": 168
+    },
+    {
+      "epoch": 0.38578680203045684,
+      "grad_norm": 2.089890718460083,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 1.5668,
+      "step": 171
+    },
+    {
+      "epoch": 0.3925549915397631,
+      "grad_norm": 1.8286525011062622,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 1.3543,
+      "step": 174
+    },
+    {
+      "epoch": 0.3993231810490694,
+      "grad_norm": 2.1308631896972656,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 1.4603,
+      "step": 177
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 2.0532541275024414,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 1.4869,
+      "step": 180
+    },
+    {
+      "epoch": 0.4128595600676819,
+      "grad_norm": 2.347409963607788,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 1.2985,
+      "step": 183
+    },
+    {
+      "epoch": 0.4196277495769882,
+      "grad_norm": 1.9288790225982666,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 1.4297,
+      "step": 186
+    },
+    {
+      "epoch": 0.4263959390862944,
+      "grad_norm": 2.8015472888946533,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 1.543,
+      "step": 189
+    },
+    {
+      "epoch": 0.43316412859560066,
+      "grad_norm": 2.930189371109009,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 1.3146,
+      "step": 192
+    },
+    {
+      "epoch": 0.43993231810490696,
+      "grad_norm": 2.7898826599121094,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 1.4502,
+      "step": 195
+    },
+    {
+      "epoch": 0.4467005076142132,
+      "grad_norm": 3.787993907928467,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 1.4229,
+      "step": 198
+    },
+    {
+      "epoch": 0.4512126339537507,
+      "eval_loss": 1.5217487812042236,
+      "eval_runtime": 55.7179,
+      "eval_samples_per_second": 13.407,
+      "eval_steps_per_second": 3.356,
+      "step": 200
     }
   ],
   "logging_steps": 3,
@@ -412,12 +532,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.995744869351424e+17,
+  "total_flos": 2.660993159135232e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null