Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4455274b171ae7b6e1809d522d744f1c2f7e23e0c739883da741ce3103201259
+oid sha256:e47ad5a153ac2d85ef55dedb30bb28ad7dea06bdd84878b438451ecc00a2b56d
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4063296823457d7f4fbc3a93cbd532f5cfd5d026a30efa22fbfa566c762f9077
+oid sha256:4cd85090c1815d57497bec2f925c88105314b856edf534ddbad351f9a143b2ed
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e587da4f7c2aeb4d259305225060892ce68d2013607bfc56b591974d450589e
+oid sha256:f1cd5d70d138c6f1347ea7cd306077c49a060192ce2ce5504c44291134068816
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4f03b7b67e98601549e21a2fe68187850c8594cc0723fe04c9bd3a0468ff1b
+oid sha256:05f9b624f76ca933a33ceb156475153beb638028e6bfc2402f5a08accb6991bc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd09c5b341331815954f296e02ce7508a7d65aea9b47883abac6b2d2f743bb76
+oid sha256:96d31ccf05bdba1cbc4b498a436f24e17ad5a1b43f6541d585f2c09bfe5ff1a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc405cc8f89b11d441ccee2cde799c4560ae6e68e834f96f0ee32529064437a1
+oid sha256:3c4b1d0d217f5ef37aff4cc7a15a912248914dae9c0f1779b50a7da7a72b48ff
 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": 4.6739654541015625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.043544524276072284,
+  "best_metric": 4.3903303146362305,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08708904855214457,
   "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": 30.238,
       "eval_steps_per_second": 3.784,
       "step": 25
+    },
+    {
+      "epoch": 0.045286305247115174,
+      "grad_norm": 13.083211898803711,
+      "learning_rate": 5e-05,
+      "loss": 5.3126,
+      "step": 26
+    },
+    {
+      "epoch": 0.047028086218158065,
+      "grad_norm": 12.418418884277344,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 5.1456,
+      "step": 27
+    },
+    {
+      "epoch": 0.048769867189200955,
+      "grad_norm": 10.2151460647583,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.7801,
+      "step": 28
+    },
+    {
+      "epoch": 0.05051164816024385,
+      "grad_norm": 8.041688919067383,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.5228,
+      "step": 29
+    },
+    {
+      "epoch": 0.05225342913128674,
+      "grad_norm": 6.638741493225098,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.687,
+      "step": 30
+    },
+    {
+      "epoch": 0.05399521010232963,
+      "grad_norm": 4.822203159332275,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.2664,
+      "step": 31
+    },
+    {
+      "epoch": 0.05573699107337252,
+      "grad_norm": 4.175324440002441,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.3138,
+      "step": 32
+    },
+    {
+      "epoch": 0.05747877204441541,
+      "grad_norm": 4.204291820526123,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.3258,
+      "step": 33
+    },
+    {
+      "epoch": 0.059220553015458303,
+      "grad_norm": 5.981131553649902,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.3003,
+      "step": 34
+    },
+    {
+      "epoch": 0.0609623339865012,
+      "grad_norm": 8.311537742614746,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.5814,
+      "step": 35
+    },
+    {
+      "epoch": 0.06270411495754409,
+      "grad_norm": 9.094008445739746,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.59,
+      "step": 36
+    },
+    {
+      "epoch": 0.06444589592858697,
+      "grad_norm": 9.825113296508789,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.5756,
+      "step": 37
+    },
+    {
+      "epoch": 0.06618767689962987,
+      "grad_norm": 4.1204705238342285,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.5113,
+      "step": 38
+    },
+    {
+      "epoch": 0.06792945787067277,
+      "grad_norm": 4.433558940887451,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 4.4955,
+      "step": 39
+    },
+    {
+      "epoch": 0.06967123884171565,
+      "grad_norm": 4.3605570793151855,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.3585,
+      "step": 40
+    },
+    {
+      "epoch": 0.07141301981275855,
+      "grad_norm": 4.073428630828857,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.1968,
+      "step": 41
+    },
+    {
+      "epoch": 0.07315480078380143,
+      "grad_norm": 3.791999340057373,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.4238,
+      "step": 42
+    },
+    {
+      "epoch": 0.07489658175484433,
+      "grad_norm": 3.7935125827789307,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 4.2672,
+      "step": 43
+    },
+    {
+      "epoch": 0.07663836272588721,
+      "grad_norm": 3.286874771118164,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.0396,
+      "step": 44
+    },
+    {
+      "epoch": 0.07838014369693011,
+      "grad_norm": 3.8434550762176514,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.0224,
+      "step": 45
+    },
+    {
+      "epoch": 0.08012192466797301,
+      "grad_norm": 4.013460159301758,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.2881,
+      "step": 46
+    },
+    {
+      "epoch": 0.08186370563901589,
+      "grad_norm": 5.182753086090088,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.4167,
+      "step": 47
+    },
+    {
+      "epoch": 0.08360548661005879,
+      "grad_norm": 8.090438842773438,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.5582,
+      "step": 48
+    },
+    {
+      "epoch": 0.08534726758110167,
+      "grad_norm": 6.627746105194092,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.5952,
+      "step": 49
+    },
+    {
+      "epoch": 0.08708904855214457,
+      "grad_norm": 9.383976936340332,
+      "learning_rate": 0.0,
+      "loss": 4.6895,
+      "step": 50
+    },
+    {
+      "epoch": 0.08708904855214457,
+      "eval_loss": 4.3903303146362305,
+      "eval_runtime": 127.9549,
+      "eval_samples_per_second": 30.229,
+      "eval_steps_per_second": 3.783,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null