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:a18ed80029ff7a873b0a22f4b9c338450e375835f7ad610e6d2f0b9257ef7d36
+oid sha256:5d124b4b30319da17cea3b15a0a3008d83796163009969ebf665e489e330dffc
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d379074ecf626a4aae6f86957d80a513012273f5e3917efe8eceeebe23e571b1
+oid sha256:70816623f618cfb1c074c4d23025ff53cb9e85cc850523e8f254a7fb7d36543d
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff803fd093f9e42549ee3f794993749d77dd1733897e6f872574c3506f222d2f
+oid sha256:d4767fd0696b8dea037776af6fdd488c8b6c9b5dda2ad3d3c7efa35dd9bc1aba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f26f8c1d804fee9670b01aeb06e38bfe96da956e9125896493bb87da74437cd
+oid sha256:9a93010836aa19192345ad419285436173865e233380f04d240e047ea2de69b9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba15e7bef57c9b7ddc6770a0692523cdc30ca05c35dceba1165c17efd56f675
+oid sha256:39e6c23a2f3989ad74de3e868afb9ce0ced19ae0a3ebfa978ba6efcd9f03d970
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb5b90cdcb5e9d334ab61b07ab8f42014e24835a93f552f18d430dfe48fc65b
+oid sha256:f3e2f985d3fadeea185910765b01df719ec815f5432c166d473254ad2eea4d3b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2685376405715942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2576489533011272,
+  "best_metric": 1.2285106182098389,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5152979066022544,
   "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": 12.321,
       "eval_steps_per_second": 3.203,
       "step": 25
+    },
+    {
+      "epoch": 0.2679549114331723,
+      "grad_norm": 0.08522077649831772,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.2349,
+      "step": 26
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 0.10480500757694244,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1812,
+      "step": 27
+    },
+    {
+      "epoch": 0.2885668276972625,
+      "grad_norm": 0.10795049369335175,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0749,
+      "step": 28
+    },
+    {
+      "epoch": 0.29887278582930754,
+      "grad_norm": 0.11765482276678085,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.0049,
+      "step": 29
+    },
+    {
+      "epoch": 0.30917874396135264,
+      "grad_norm": 0.12303701788187027,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0885,
+      "step": 30
+    },
+    {
+      "epoch": 0.31948470209339774,
+      "grad_norm": 0.12804476916790009,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9557,
+      "step": 31
+    },
+    {
+      "epoch": 0.32979066022544284,
+      "grad_norm": 0.15007159113883972,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0325,
+      "step": 32
+    },
+    {
+      "epoch": 0.34009661835748795,
+      "grad_norm": 0.16402068734169006,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.053,
+      "step": 33
+    },
+    {
+      "epoch": 0.350402576489533,
+      "grad_norm": 0.19465193152427673,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1747,
+      "step": 34
+    },
+    {
+      "epoch": 0.3607085346215781,
+      "grad_norm": 0.220439612865448,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2401,
+      "step": 35
+    },
+    {
+      "epoch": 0.3710144927536232,
+      "grad_norm": 0.24589957296848297,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3254,
+      "step": 36
+    },
+    {
+      "epoch": 0.3813204508856683,
+      "grad_norm": 0.3180951178073883,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.3382,
+      "step": 37
+    },
+    {
+      "epoch": 0.39162640901771334,
+      "grad_norm": 0.10987213253974915,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2727,
+      "step": 38
+    },
+    {
+      "epoch": 0.40193236714975844,
+      "grad_norm": 0.08961351960897446,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.194,
+      "step": 39
+    },
+    {
+      "epoch": 0.41223832528180354,
+      "grad_norm": 0.1107921153306961,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.1653,
+      "step": 40
+    },
+    {
+      "epoch": 0.42254428341384864,
+      "grad_norm": 0.10833823680877686,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1058,
+      "step": 41
+    },
+    {
+      "epoch": 0.43285024154589374,
+      "grad_norm": 0.12067985534667969,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0183,
+      "step": 42
+    },
+    {
+      "epoch": 0.4431561996779388,
+      "grad_norm": 0.11738017201423645,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9988,
+      "step": 43
+    },
+    {
+      "epoch": 0.4534621578099839,
+      "grad_norm": 0.12681663036346436,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0255,
+      "step": 44
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.14073887467384338,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9381,
+      "step": 45
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 0.16310881078243256,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1671,
+      "step": 46
+    },
+    {
+      "epoch": 0.48438003220611914,
+      "grad_norm": 0.18224647641181946,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1381,
+      "step": 47
+    },
+    {
+      "epoch": 0.49468599033816424,
+      "grad_norm": 0.21813221275806427,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2998,
+      "step": 48
+    },
+    {
+      "epoch": 0.5049919484702093,
+      "grad_norm": 0.25227874517440796,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2613,
+      "step": 49
+    },
+    {
+      "epoch": 0.5152979066022544,
+      "grad_norm": 0.4172573983669281,
+      "learning_rate": 1e-05,
+      "loss": 1.2811,
+      "step": 50
+    },
+    {
+      "epoch": 0.5152979066022544,
+      "eval_loss": 1.2285106182098389,
+      "eval_runtime": 4.0411,
+      "eval_samples_per_second": 12.373,
+      "eval_steps_per_second": 3.217,
+      "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": 2.8164227105554432e+17,
+  "total_flos": 5.6319666600647066e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null