Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ca766c151b32bea39e962f972d34a7c85cbc8a1b3788ad060770599d94fb68
+oid sha256:f8391bfeb9ed2019fe10bbc6879305a69876a37d2f145c44ff1f2177286df45d
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b467804b78757374d3c455c1b9eb778d60453420ff0d3945c080d2a803f59b
+oid sha256:8c82acfea253d6a2fe75ddf8c29af011bcac71fdc5ce516e493db4b78aeb6c4e
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae572824315aa08c91e4cea0f09bfc4901dc0dd44ef66c81061183ae681fb37
+oid sha256:3b51304c6953095cd67aca9f9590fb778b6958fd2fc5a6bf9501f9fd0b8fd18b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d36a8fdf8267aafe7616310856d4f11f1f20ec0bbd9be0939b2b8ddf86bfccb
+oid sha256:c06cbe91c169c4128d119f2555f4b07bd738fe69cc22af98c623896fa8876fc3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b89a9b7ff2719974db47bf0cdc497893563b9420948695daa271dd45517a3f
+oid sha256:873fc9092cf9dac55d0c670ed665c7d043d065cccbee750e176863845bb84fc9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4bf49801d68b4610d4416ed2c4ed33aad26555b689be5157838ec177c39041
+oid sha256:d950ec7131bae000403e95d7a3e6e81fea115d1560c8884c50c9a22acfc2cfca
 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": 1.666447401046753,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01242544731610338,
+  "best_metric": 1.196676254272461,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02485089463220676,
   "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": 72.051,
       "eval_steps_per_second": 9.01,
       "step": 25
+    },
+    {
+      "epoch": 0.012922465208747515,
+      "grad_norm": 3.7888262271881104,
+      "learning_rate": 5e-05,
+      "loss": 3.774,
+      "step": 26
+    },
+    {
+      "epoch": 0.01341948310139165,
+      "grad_norm": 3.884737253189087,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 4.2024,
+      "step": 27
+    },
+    {
+      "epoch": 0.013916500994035786,
+      "grad_norm": 1.4736801385879517,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8939,
+      "step": 28
+    },
+    {
+      "epoch": 0.01441351888667992,
+      "grad_norm": 1.3907657861709595,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9733,
+      "step": 29
+    },
+    {
+      "epoch": 0.014910536779324055,
+      "grad_norm": 1.3196364641189575,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9697,
+      "step": 30
+    },
+    {
+      "epoch": 0.015407554671968192,
+      "grad_norm": 1.3449130058288574,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9002,
+      "step": 31
+    },
+    {
+      "epoch": 0.015904572564612324,
+      "grad_norm": 1.2147306203842163,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8903,
+      "step": 32
+    },
+    {
+      "epoch": 0.016401590457256462,
+      "grad_norm": 1.1119961738586426,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7223,
+      "step": 33
+    },
+    {
+      "epoch": 0.016898608349900597,
+      "grad_norm": 1.2433083057403564,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8289,
+      "step": 34
+    },
+    {
+      "epoch": 0.01739562624254473,
+      "grad_norm": 1.4834322929382324,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.877,
+      "step": 35
+    },
+    {
+      "epoch": 0.017892644135188866,
+      "grad_norm": 1.5780261754989624,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0768,
+      "step": 36
+    },
+    {
+      "epoch": 0.018389662027833,
+      "grad_norm": 1.4980250597000122,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9905,
+      "step": 37
+    },
+    {
+      "epoch": 0.018886679920477135,
+      "grad_norm": 3.0528273582458496,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9373,
+      "step": 38
+    },
+    {
+      "epoch": 0.019383697813121274,
+      "grad_norm": 6.350691795349121,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.6548,
+      "step": 39
+    },
+    {
+      "epoch": 0.019880715705765408,
+      "grad_norm": 3.366940975189209,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.4144,
+      "step": 40
+    },
+    {
+      "epoch": 0.020377733598409543,
+      "grad_norm": 1.3775631189346313,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8298,
+      "step": 41
+    },
+    {
+      "epoch": 0.020874751491053677,
+      "grad_norm": 1.1670130491256714,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.74,
+      "step": 42
+    },
+    {
+      "epoch": 0.021371769383697812,
+      "grad_norm": 1.1070308685302734,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6431,
+      "step": 43
+    },
+    {
+      "epoch": 0.02186878727634195,
+      "grad_norm": 1.2304421663284302,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7972,
+      "step": 44
+    },
+    {
+      "epoch": 0.022365805168986085,
+      "grad_norm": 1.2622898817062378,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7058,
+      "step": 45
+    },
+    {
+      "epoch": 0.02286282306163022,
+      "grad_norm": 1.2102621793746948,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8584,
+      "step": 46
+    },
+    {
+      "epoch": 0.023359840954274354,
+      "grad_norm": 1.2043925523757935,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7105,
+      "step": 47
+    },
+    {
+      "epoch": 0.02385685884691849,
+      "grad_norm": 1.2344636917114258,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7777,
+      "step": 48
+    },
+    {
+      "epoch": 0.024353876739562623,
+      "grad_norm": 1.6974679231643677,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.901,
+      "step": 49
+    },
+    {
+      "epoch": 0.02485089463220676,
+      "grad_norm": 1.5023279190063477,
+      "learning_rate": 0.0,
+      "loss": 0.8633,
+      "step": 50
+    },
+    {
+      "epoch": 0.02485089463220676,
+      "eval_loss": 1.196676254272461,
+      "eval_runtime": 188.4336,
+      "eval_samples_per_second": 71.935,
+      "eval_steps_per_second": 8.995,
+      "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": 6.158555082129408e+16,
+  "total_flos": 1.2250889150529536e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null