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:e7a8a1f08c47e50bd3c08e3ee335cf9938cc8c362a8bc5b398c681ccabf2809f
+oid sha256:8683728e8d04f69b75d7476c9345aa2531c7cbe9cd3905ce8bac7691f4fdce7d
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb77ba9f60e0908b1a60d7c75736a23bcf7167f88a7e929ef35fe59458037dc
+oid sha256:8954cc29236e4087d998ec1b66605b0c1c0110191204243cec26ddadd0bbf166
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8aa6bcfa2dd45e6c992d692a6f2dd5da4f634e35af4fe44f599d6d607c3e15e
+oid sha256:51c02da99d1f520dbaffcac8e818164a15b6c3866ebad2f59cf373fdeeb1128f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea513f812a98168dbe98c8c8b73feafa925a0fd28cc6a8320e56d779c882238
+oid sha256:bdacda0f8c508fef7cb657929773b48c5656cff7922fdf548789c1d58b805520
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de9e6c4543b14cf287d5462f7dc057d01f139b6c7a7aea1f1c4eea031b46f3a3
+oid sha256:afa4601a08d8b1245b5cdbe13cf3636004cde289aa2992e54f0afd219e492945
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf23f24684e57b6e4a66cce0183d733669844a008c7a9ddc57af6dcc3eeef063
+oid sha256:86b0bc6947975917d4ea80366acf94af81cf3a1343d58a960d62380543ce705a
 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": 5.363160133361816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009473509698505553,
+  "best_metric": 4.832469463348389,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.018947019397011107,
   "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": 357.568,
       "eval_steps_per_second": 44.711,
       "step": 25
+    },
+    {
+      "epoch": 0.009852450086445776,
+      "grad_norm": 2.8592782020568848,
+      "learning_rate": 5e-05,
+      "loss": 5.1642,
+      "step": 26
+    },
+    {
+      "epoch": 0.010231390474385997,
+      "grad_norm": 3.3668901920318604,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 4.9931,
+      "step": 27
+    },
+    {
+      "epoch": 0.01061033086232622,
+      "grad_norm": 3.769247531890869,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 5.0043,
+      "step": 28
+    },
+    {
+      "epoch": 0.010989271250266443,
+      "grad_norm": 4.0553297996521,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 5.0804,
+      "step": 29
+    },
+    {
+      "epoch": 0.011368211638206664,
+      "grad_norm": 3.99537992477417,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 5.123,
+      "step": 30
+    },
+    {
+      "epoch": 0.011747152026146887,
+      "grad_norm": 4.698930263519287,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 5.0135,
+      "step": 31
+    },
+    {
+      "epoch": 0.012126092414087108,
+      "grad_norm": 4.247986316680908,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.9207,
+      "step": 32
+    },
+    {
+      "epoch": 0.012505032802027331,
+      "grad_norm": 3.5553126335144043,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.9427,
+      "step": 33
+    },
+    {
+      "epoch": 0.012883973189967554,
+      "grad_norm": 3.068984031677246,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.9177,
+      "step": 34
+    },
+    {
+      "epoch": 0.013262913577907775,
+      "grad_norm": 3.0896942615509033,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.9117,
+      "step": 35
+    },
+    {
+      "epoch": 0.013641853965847998,
+      "grad_norm": 2.157078266143799,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.8537,
+      "step": 36
+    },
+    {
+      "epoch": 0.014020794353788219,
+      "grad_norm": 3.4221081733703613,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 5.1317,
+      "step": 37
+    },
+    {
+      "epoch": 0.014399734741728442,
+      "grad_norm": 2.8120241165161133,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.0818,
+      "step": 38
+    },
+    {
+      "epoch": 0.014778675129668664,
+      "grad_norm": 3.566973924636841,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 4.7874,
+      "step": 39
+    },
+    {
+      "epoch": 0.015157615517608886,
+      "grad_norm": 3.3742949962615967,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.8105,
+      "step": 40
+    },
+    {
+      "epoch": 0.015536555905549108,
+      "grad_norm": 2.7615294456481934,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.736,
+      "step": 41
+    },
+    {
+      "epoch": 0.01591549629348933,
+      "grad_norm": 2.8716986179351807,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.8706,
+      "step": 42
+    },
+    {
+      "epoch": 0.016294436681429554,
+      "grad_norm": 2.268878221511841,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.0533,
+      "step": 43
+    },
+    {
+      "epoch": 0.016673377069369773,
+      "grad_norm": 2.9596915245056152,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.745,
+      "step": 44
+    },
+    {
+      "epoch": 0.017052317457309996,
+      "grad_norm": 2.2583632469177246,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.6773,
+      "step": 45
+    },
+    {
+      "epoch": 0.01743125784525022,
+      "grad_norm": 3.824549674987793,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.8859,
+      "step": 46
+    },
+    {
+      "epoch": 0.017810198233190442,
+      "grad_norm": 2.705209970474243,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.986,
+      "step": 47
+    },
+    {
+      "epoch": 0.018189138621130665,
+      "grad_norm": 2.4990625381469727,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.0115,
+      "step": 48
+    },
+    {
+      "epoch": 0.018568079009070884,
+      "grad_norm": 2.7045373916625977,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.8936,
+      "step": 49
+    },
+    {
+      "epoch": 0.018947019397011107,
+      "grad_norm": 3.766317367553711,
+      "learning_rate": 0.0,
+      "loss": 5.2797,
+      "step": 50
+    },
+    {
+      "epoch": 0.018947019397011107,
+      "eval_loss": 4.832469463348389,
+      "eval_runtime": 49.6333,
+      "eval_samples_per_second": 358.187,
+      "eval_steps_per_second": 44.788,
+      "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": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null