Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21bb9f54767b3aef1942435116c8cd2df583d05ae2cbfd9b0a3ecab2fe452876
+oid sha256:9c4c20d5aee733fdf3eb6b75cdc4d27069ab489cbf0ba39236996f787accdba3
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17452d05a2e7aaceaae7e72a4f2efb64b1daffad68aa507202b86a8b089d52db
+oid sha256:06dd9e0bb6b09199b9318dbc09861fa957a881f62a9db4ac49beb27b66607d76
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad21eb96431e161af9072624940931c6add529b71a10c6b0e8f6f9f767d12b1
+oid sha256:b394e99e09d5bc77397e023b84cb79a14354b4af9def531a73fb8c4bf0e7ab52
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0c5ce1e6dcfbf3ea34c42df99cb42484b6b9457a635261a1dcf7666dfed168
+oid sha256:9018e4ba27a7db3efa23838ce1e2daa196b0bc999b9c6d842f482389c74ad374
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643d0225a289fa89a97f8d6aa4311d59a53c9ea8b756db5be9259b03b2c4fc4e
+oid sha256:596c23174bd9481a95445344927b39c0b773ba68c1facdd1f58031689b31b0f4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb868e39f0aeb10566289d9b22930bf151e9fe1d8213bec48d7f56a12601ac4
+oid sha256:43e55aeeea11e7cae671971bd97045f6b585c019e18e49b329bd6337a97a7d2f
 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": 0.40415117144584656,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9153318077803204,
+  "best_metric": 0.3631051480770111,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.8398169336384438,
   "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": 35.448,
       "eval_steps_per_second": 4.431,
       "step": 25
+    },
+    {
+      "epoch": 0.9519450800915332,
+      "grad_norm": 0.15927977859973907,
+      "learning_rate": 5e-05,
+      "loss": 0.3694,
+      "step": 26
+    },
+    {
+      "epoch": 0.988558352402746,
+      "grad_norm": 0.22202396392822266,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4189,
+      "step": 27
+    },
+    {
+      "epoch": 1.034324942791762,
+      "grad_norm": 0.2729898989200592,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7635,
+      "step": 28
+    },
+    {
+      "epoch": 1.070938215102975,
+      "grad_norm": 0.12082233279943466,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3147,
+      "step": 29
+    },
+    {
+      "epoch": 1.1075514874141876,
+      "grad_norm": 0.1213618814945221,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2839,
+      "step": 30
+    },
+    {
+      "epoch": 1.1441647597254005,
+      "grad_norm": 0.13045448064804077,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2742,
+      "step": 31
+    },
+    {
+      "epoch": 1.1807780320366132,
+      "grad_norm": 0.15795262157917023,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3233,
+      "step": 32
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 0.1785769909620285,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3381,
+      "step": 33
+    },
+    {
+      "epoch": 1.2540045766590389,
+      "grad_norm": 0.16711662709712982,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4122,
+      "step": 34
+    },
+    {
+      "epoch": 1.2906178489702518,
+      "grad_norm": 0.1267433911561966,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.335,
+      "step": 35
+    },
+    {
+      "epoch": 1.3272311212814645,
+      "grad_norm": 0.11527062207460403,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2862,
+      "step": 36
+    },
+    {
+      "epoch": 1.3638443935926774,
+      "grad_norm": 0.11933337897062302,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2703,
+      "step": 37
+    },
+    {
+      "epoch": 1.40045766590389,
+      "grad_norm": 0.13421335816383362,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2857,
+      "step": 38
+    },
+    {
+      "epoch": 1.437070938215103,
+      "grad_norm": 0.15082192420959473,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3248,
+      "step": 39
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.19551853835582733,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.349,
+      "step": 40
+    },
+    {
+      "epoch": 1.5102974828375286,
+      "grad_norm": 0.13802577555179596,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3084,
+      "step": 41
+    },
+    {
+      "epoch": 1.5469107551487413,
+      "grad_norm": 0.12603098154067993,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3111,
+      "step": 42
+    },
+    {
+      "epoch": 1.5835240274599542,
+      "grad_norm": 0.11855199933052063,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2727,
+      "step": 43
+    },
+    {
+      "epoch": 1.6201372997711672,
+      "grad_norm": 0.12961673736572266,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2666,
+      "step": 44
+    },
+    {
+      "epoch": 1.6567505720823799,
+      "grad_norm": 0.13719911873340607,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3096,
+      "step": 45
+    },
+    {
+      "epoch": 1.6933638443935926,
+      "grad_norm": 0.16374927759170532,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3387,
+      "step": 46
+    },
+    {
+      "epoch": 1.7299771167048055,
+      "grad_norm": 0.21558819711208344,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3526,
+      "step": 47
+    },
+    {
+      "epoch": 1.7665903890160184,
+      "grad_norm": 0.11992810666561127,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3078,
+      "step": 48
+    },
+    {
+      "epoch": 1.803203661327231,
+      "grad_norm": 0.12123319506645203,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3008,
+      "step": 49
+    },
+    {
+      "epoch": 1.8398169336384438,
+      "grad_norm": 0.11846727877855301,
+      "learning_rate": 0.0,
+      "loss": 0.279,
+      "step": 50
+    },
+    {
+      "epoch": 1.8398169336384438,
+      "eval_loss": 0.3631051480770111,
+      "eval_runtime": 5.1867,
+      "eval_samples_per_second": 35.476,
+      "eval_steps_per_second": 4.434,
+      "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": 2.8419067379449856e+17,
+  "total_flos": 5.6855709765074944e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null