Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2b604c7f93f568badf0cdf82eb43d23ab3129bf4c6f894a64c83c43f9cb4f1
+oid sha256:44e6612e6e141f53244c8a4cb54c34e3cb0f177abc61c4d49c1072fa87738d8c
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6578a7506fc030918f9190df0291117a57799a6b39d96b4ffa499b3ea983200
+oid sha256:a48a3260ada7ec5afe10face1738bcf43e9aba6da7b13a7d172349d787fe83e6
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b16b085d408cbbb65b90d88890c6af4933f1efd7b2bf2d462fc7aa151356619
+oid sha256:aa88b02b72b8c2a555796c0d7631906a106285b92f881bf3910d08a4cad29f8a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d716fd2edd4b49109a8affe49d0b15fa6fb03955e276b16f47ee09e3d0a35595
+oid sha256:46bed96a4022ef45db08426815827f4571434d0530a907e787a9165d94b6580f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c2ad8f32aa729ce75f5f3d35a12e00ea53b69aa662cc7ff94f6659cb63e5ac
+oid sha256:d793f74df7f353100368b6893a770f6ee02ad281841db8be598cec445ebffd56
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c93ab429a5e70813d98ba94c6813b3b09e276c8b6af7bedaf6c224877255b94
+oid sha256:6fa945bf95d687b412fe300b7b92c6fa900feee8264bfdf097f144d929b94dec
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270f031239c90143a69a5e3103494133e68e56d7495d4d43bd4cf80bb106050c
+oid sha256:1d29324a0d5877763002861a44f469da99d01dae7b8684c45bb1b74d6def2b49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5595415830612183,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7857142857142856,
+  "epoch": 3.0,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 18.691,
       "eval_steps_per_second": 2.361,
       "step": 25
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.09571477770805359,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.5863,
+      "step": 26
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.12938934564590454,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5949,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.10131942480802536,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.5571,
+      "step": 28
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.09410589933395386,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.5145,
+      "step": 29
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.08397644758224487,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.5647,
+      "step": 30
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.11132214218378067,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.5738,
+      "step": 31
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.08569318056106567,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5266,
+      "step": 32
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.07982096821069717,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.5492,
+      "step": 33
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.0867500901222229,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5342,
+      "step": 34
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08213593065738678,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.522,
+      "step": 35
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.07767733931541443,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.5404,
+      "step": 36
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.08701010048389435,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5392,
+      "step": 37
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.08963371813297272,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.5274,
+      "step": 38
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.08364277333021164,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.5252,
+      "step": 39
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.08037589490413666,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.5553,
+      "step": 40
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.10078304260969162,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.5689,
+      "step": 41
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.07615384459495544,
+      "learning_rate": 0.0,
+      "loss": 0.5335,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.5974533229287834e+17,
+  "total_flos": 9.40663836438954e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null