Training in progress, step 2850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d8105e08b44734413954313ee3f59582f2323ad431f91a8d42d31e834f41c4c
+oid sha256:1404e60fabb5103dbe434a7e9d7d0543eaa50c6cb487e2d805559319b22760ea
 size 18516456

last-checkpoint/global_step2849/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0320fc7e79afa52871fad11b4951ff226723ea958a8c75baa66260e01590d00
+size 27700976

last-checkpoint/global_step2849/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493d98c40644d4613b7287b8a8e89c29c6bcafd90c3423ade06378a38611b230
+size 27700976

last-checkpoint/global_step2849/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da8ec6e6b06c57bc2017e5fd74916f5c7af2806159816995dbd17d2cba41093
+size 27700976

last-checkpoint/global_step2849/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c5c17e53354433c9101c2204b9529ff9ca60c9fa6419f900cd02cf5bcf7e14
+size 27700976

last-checkpoint/global_step2849/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c59124c63278e0ddcdd00d2485f23837eb1e4a24778f31cd0a1f29b7f5ebaf2
+size 411571

last-checkpoint/global_step2849/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fcc75c180d57d0d5cf6ee78c7397542385f0b34c59f3995878fbc1639b1c23
+size 411507

last-checkpoint/global_step2849/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aee38319c36ef0c2fddef1bce787e579f51b9dddc8aade89ea73123165b1ea4
+size 411507

last-checkpoint/global_step2849/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a435cae583755a87893c919608846d626e54fee7180a95a616df5408f65cbf7d
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step2799
+global_step2849

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8dba2341c0517760edfde50521977f02a5bd982ffd3bc03de6109439c4f478
+oid sha256:ce92cea831a04716b4b472f1dad1cc986b2021dee9aac057217f5d455b27ec42
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2bf831df9fbade9ac2a8db79798bc2a7b1afb85a78a6e463ec7a7db4acc0f8e
+oid sha256:3cddb73bbdf0f6f6a2c3182d70f7ad5d587353b164c08dd4f383b940d6b61e4e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8602ff0a0fa366d46b61c0ef2b23ce468387898cf2bc1027e5450de73ddf647f
+oid sha256:b24b508e466beb446d37377d2a04757d3bc2b4230de3ac56b25a65d7753a74c1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb51d675cf23603b1b765cd645f53d6b66ddb104d56d48674e9c798e086f696
+oid sha256:b4c6a18a7de8b25b21673ba2ff7efbaaae00ec8c453c7975b467c1df87b87022
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a7c605cf80a46d2e0c661d5469c16671b681f268e3ecd5d1d64188653910db
+oid sha256:28cb8f1d536b1fc196e353ec37fd07d574fab0a464ddd8b31c73c59dcab3c03b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6319106221199036,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-1600",
-  "epoch": 1.4419263456090652,
+  "epoch": 1.467679629152717,
   "eval_steps": 50,
-  "global_step": 2800,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4991,11 +4991,100 @@
       "eval_steps_per_second": 0.931,
       "num_input_tokens_seen": 32743032,
       "step": 2800
+    },
+    {
+      "epoch": 1.4445016739634302,
+      "grad_norm": 4.932628514942533,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.2974,
+      "num_input_tokens_seen": 32801504,
+      "step": 2805
+    },
+    {
+      "epoch": 1.4470770023177955,
+      "grad_norm": 8.764444587690557,
+      "learning_rate": 8.009177137203794e-06,
+      "loss": 0.2849,
+      "num_input_tokens_seen": 32860032,
+      "step": 2810
+    },
+    {
+      "epoch": 1.4496523306721607,
+      "grad_norm": 5.502098759051231,
+      "learning_rate": 7.877671276687898e-06,
+      "loss": 0.3024,
+      "num_input_tokens_seen": 32918472,
+      "step": 2815
+    },
+    {
+      "epoch": 1.452227659026526,
+      "grad_norm": 3.2634043608450183,
+      "learning_rate": 7.747161615458902e-06,
+      "loss": 0.2565,
+      "num_input_tokens_seen": 32976944,
+      "step": 2820
+    },
+    {
+      "epoch": 1.4548029873808912,
+      "grad_norm": 4.852977750360098,
+      "learning_rate": 7.617651240089546e-06,
+      "loss": 0.2473,
+      "num_input_tokens_seen": 33035424,
+      "step": 2825
+    },
+    {
+      "epoch": 1.4573783157352562,
+      "grad_norm": 8.667293936674204,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 0.3118,
+      "num_input_tokens_seen": 33093880,
+      "step": 2830
+    },
+    {
+      "epoch": 1.4599536440896215,
+      "grad_norm": 9.253351843058615,
+      "learning_rate": 7.361640574981937e-06,
+      "loss": 0.2593,
+      "num_input_tokens_seen": 33152328,
+      "step": 2835
+    },
+    {
+      "epoch": 1.4625289724439865,
+      "grad_norm": 6.811131820051524,
+      "learning_rate": 7.2351463399336735e-06,
+      "loss": 0.284,
+      "num_input_tokens_seen": 33210816,
+      "step": 2840
+    },
+    {
+      "epoch": 1.4651043007983517,
+      "grad_norm": 4.086720732934785,
+      "learning_rate": 7.109663499981834e-06,
+      "loss": 0.2671,
+      "num_input_tokens_seen": 33269320,
+      "step": 2845
+    },
+    {
+      "epoch": 1.467679629152717,
+      "grad_norm": 9.463519299706055,
+      "learning_rate": 6.985195022814067e-06,
+      "loss": 0.2848,
+      "num_input_tokens_seen": 33327720,
+      "step": 2850
+    },
+    {
+      "epoch": 1.467679629152717,
+      "eval_loss": 0.8045337796211243,
+      "eval_runtime": 15.9996,
+      "eval_samples_per_second": 3.75,
+      "eval_steps_per_second": 0.938,
+      "num_input_tokens_seen": 33327720,
+      "step": 2850
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 32743032,
+  "num_input_tokens_seen": 33327720,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -5010,7 +5099,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1838675721715712.0,
+  "total_flos": 1871508641415168.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null