Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38045c5e5f16f09c87f9a0463a3998e8dc95f4c3fa78121525c3cbede5fa2137
+oid sha256:d3a6d9dcb110b329f5da1f89927c0606c8dc8da79fc27ef05cadc3e02a20cf61
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0fb7dd40910c1443813f9605e9a265767af94836761ab6eff44eb308e7187f
+oid sha256:a603bcfccb46b28779c1e73ae36bd2b5bbc44ce57bc49b18849da2d11746545b
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5cba2ccee155ab788c7c38312665a2aebadece18f8cde2ac9726630a4c1177
+oid sha256:d950c9c30fe0369cf923e718e5fd7bf4dd0a0d326cd18dfd8ba6e7655bd688d4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5409a392445b9b76a63e37df350c3ae3d8dfa2b5f6351f317f692f2a613651ed
+oid sha256:6f6a721b716f593564813166272b273a13b62c82991cdf085a9ac4bba0b15ad1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb3c1db513b56ec65f4d2dc3ec9c58e78488649072118ad520cab7ec1ed482a
+oid sha256:e8b52973db9f6fc47dccaf8f4504a23f59a98b498141e07813fa90a5a0a45fed
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fab340883337a39731c01960f1461c4601c48d0acdd78b27ab45127419efa4f
+oid sha256:f624ab1c98d500a61863849417b3f7897a4482f72213c2b5be89add91b298178
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9493563771247864,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1299435028248588,
+  "best_metric": 0.9366380572319031,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.2598870056497176,
   "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": 21.063,
       "eval_steps_per_second": 2.686,
       "step": 25
+    },
+    {
+      "epoch": 1.1751412429378532,
+      "grad_norm": 0.13968133926391602,
+      "learning_rate": 5e-05,
+      "loss": 0.9774,
+      "step": 26
+    },
+    {
+      "epoch": 1.2203389830508475,
+      "grad_norm": 0.20083756744861603,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0867,
+      "step": 27
+    },
+    {
+      "epoch": 1.2655367231638417,
+      "grad_norm": 0.0883803591132164,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7986,
+      "step": 28
+    },
+    {
+      "epoch": 1.310734463276836,
+      "grad_norm": 0.0967683270573616,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9001,
+      "step": 29
+    },
+    {
+      "epoch": 1.3559322033898304,
+      "grad_norm": 0.10467801243066788,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8887,
+      "step": 30
+    },
+    {
+      "epoch": 1.4011299435028248,
+      "grad_norm": 0.12629304826259613,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9147,
+      "step": 31
+    },
+    {
+      "epoch": 1.4463276836158192,
+      "grad_norm": 0.15558573603630066,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9604,
+      "step": 32
+    },
+    {
+      "epoch": 1.4915254237288136,
+      "grad_norm": 0.30503368377685547,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2131,
+      "step": 33
+    },
+    {
+      "epoch": 1.536723163841808,
+      "grad_norm": 0.08666601777076721,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8113,
+      "step": 34
+    },
+    {
+      "epoch": 1.5819209039548023,
+      "grad_norm": 0.10060662031173706,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8429,
+      "step": 35
+    },
+    {
+      "epoch": 1.6271186440677967,
+      "grad_norm": 0.1265161782503128,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8955,
+      "step": 36
+    },
+    {
+      "epoch": 1.672316384180791,
+      "grad_norm": 0.14413928985595703,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9875,
+      "step": 37
+    },
+    {
+      "epoch": 1.7175141242937855,
+      "grad_norm": 0.19615449011325836,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0382,
+      "step": 38
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": 0.09353553503751755,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7597,
+      "step": 39
+    },
+    {
+      "epoch": 1.807909604519774,
+      "grad_norm": 0.1021425724029541,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8842,
+      "step": 40
+    },
+    {
+      "epoch": 1.8531073446327684,
+      "grad_norm": 0.11777127534151077,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8963,
+      "step": 41
+    },
+    {
+      "epoch": 1.8983050847457628,
+      "grad_norm": 0.13572406768798828,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9136,
+      "step": 42
+    },
+    {
+      "epoch": 1.943502824858757,
+      "grad_norm": 0.180810809135437,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9424,
+      "step": 43
+    },
+    {
+      "epoch": 1.9887005649717513,
+      "grad_norm": 0.32613012194633484,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2046,
+      "step": 44
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": 0.22946643829345703,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5967,
+      "step": 45
+    },
+    {
+      "epoch": 2.07909604519774,
+      "grad_norm": 0.10317717492580414,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7804,
+      "step": 46
+    },
+    {
+      "epoch": 2.1242937853107344,
+      "grad_norm": 0.1184142455458641,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8891,
+      "step": 47
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.13897018134593964,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9444,
+      "step": 48
+    },
+    {
+      "epoch": 2.214689265536723,
+      "grad_norm": 0.20523014664649963,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0576,
+      "step": 49
+    },
+    {
+      "epoch": 2.2598870056497176,
+      "grad_norm": 0.10931195318698883,
+      "learning_rate": 0.0,
+      "loss": 0.7252,
+      "step": 50
+    },
+    {
+      "epoch": 2.2598870056497176,
+      "eval_loss": 0.9366380572319031,
+      "eval_runtime": 7.1084,
+      "eval_samples_per_second": 20.961,
+      "eval_steps_per_second": 2.673,
+      "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": 5.6078704654575206e+17,
+  "total_flos": 1.1215740952389878e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null